© 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. 27-TRANSCODER-HP
    7. 8969
    Prev
    Next
    INDEX
    Explanations

    if

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circumstances
    -0.29
    对æīĭ
    -0.28
    æĭĶ
    -0.26
     conf
    -0.26
    使
    -0.25
    åħ·ä½ĵæĥħåĨµ
    -0.25
    indre
    -0.25
     the
    -0.25
    åĮħ
    -0.24
    cuts
    -0.24
    POSITIVE LOGITS
    è¿Ļæł·åģļ
    0.26
    æŃ£åľ¨
    0.25
     atol
    0.24
     launching
    0.24
    æĢİä¹Īæł·
    0.24
    åĨ²åĬ¨
    0.24
    åģļä»Ģä¹Ī
    0.24
    ENDING
    0.24
     king
    0.23
     underway
    0.23
    Activations Density 0.003%

    No Known Activations