© 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. 8917
    Prev
    Next
    INDEX
    Explanations

    of

    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
     consumes
    -0.26
     disastr
    -0.25
     potrze
    -0.25
    éĻ¤éĿŀ
    -0.25
    interfaces
    -0.25
    ahead
    -0.25
    utdown
    -0.25
    .mass
    -0.24
     marry
    -0.24
    liest
    -0.24
    POSITIVE LOGITS
     an
    0.41
     pre
    0.35
     a
    0.32
     carefully
    0.31
     regular
    0.29
     Sou
    0.29
     clear
    0.28
     animal
    0.27
     free
    0.27
    mdir
    0.27
    Activations Density 0.008%

    No Known Activations