© 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. 96439
    Prev
    Next
    INDEX
    Explanations

    odds

    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
     Occup
    -0.26
    rost
    -0.25
    (_,
    -0.25
    .instant
    -0.24
    “(
    -0.24
    osti
    -0.24
    Occup
    -0.24
    ä¸Ģ个éĹ®é¢ĺ
    -0.24
    ä»İä¸Ń
    -0.24
     lado
    -0.23
    POSITIVE LOGITS
     against
    0.40
     Against
    0.33
     contre
    0.32
     of
    0.31
    favor
    0.30
    against
    0.30
    pay
    0.30
     favor
    0.30
     favorable
    0.30
     ratio
    0.30
    Activations Density 0.885%

    No Known Activations