© 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. 30-TRANSCODER-HP
    7. 95775
    Prev
    Next
    INDEX
    Explanations

    8

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aut
    -0.31
     aut
    -0.30
     sur
    -0.30
     Sur
    -0.28
    Aut
    -0.27
     Aut
    -0.27
    æºľ
    -0.27
    ideon
    -0.26
    olid
    -0.26
     Primitive
    -0.26
    POSITIVE LOGITS
    åŁķ
    0.30
    æį¨
    0.25
    é¹³
    0.24
    zsche
    0.24
    izzes
    0.24
    fts
    0.23
    _FT
    0.23
    ä¸į失
    0.23
    emens
    0.23
    èĪį
    0.23
    Activations Density 0.886%

    No Known Activations