© 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. 58043
    Prev
    Next
    INDEX
    Explanations

    free

    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
     in
    -0.44
     for
    -0.41
     as
    -0.39
     with
    -0.38
     to
    -0.37
     elsewhere
    -0.36
    çŁ£
    -0.36
     throughout
    -0.36
     on
    -0.35
     from
    -0.35
    POSITIVE LOGITS
    /of
    0.32
    æĥħåĨµè¿Ľè¡Į
    0.29
    éĹ®é¢ĺæĺ¯
    0.27
    eroon
    0.27
    unded
    0.26
    åīįæıIJæĺ¯
    0.25
    hower
    0.25
    plemented
    0.25
    sez
    0.25
    ESIS
    0.25
    Activations Density 0.009%

    No Known Activations