© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149837
    Prev
    Next
    INDEX
    Explanations

    Technical instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĥħåĨµä¸ĭ
    -0.68
    æĿ¡ä»¶ä¸ĭ
    -0.61
    çĬ¶æĢģä¸ĭ
    -0.56
    åŁºç¡Ģä¸Ĭ
    -0.53
    æŶéĹ´åĨħ
    -0.50
    æĦıä¹īä¸Ĭ
    -0.48
    çļĦæĥħåĨµä¸ĭ
    -0.48
    è¿ĩç¨ĭä¸Ń
    -0.47
    çļĦåŁºç¡Ģä¸Ĭ
    -0.46
    èĥĮæĻ¯ä¸ĭ
    -0.44
    POSITIVE LOGITS
    ä½Ĩå¦Ĥæŀľ
    0.29
    _REGISTRY
    0.26
    ridor
    0.26
     simples
    0.25
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.25
     over
    0.24
    åºıå¹ķ
    0.24
     Cue
    0.24
    za
    0.24
    ä¸ĢåĽŀäºĭ
    0.23
    Activations Density 1.332%

    No Known Activations