© 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. 96159
    Prev
    Next
    INDEX
    Explanations

    bewild

    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
    -faced
    -0.27
     torch
    -0.24
    éĢĢåĽŀ
    -0.24
     intersect
    -0.24
     devil
    -0.23
     Torch
    -0.23
    _scal
    -0.23
     creating
    -0.23
    åĪĽåĬŀ
    -0.23
    OUN
    -0.23
    POSITIVE LOGITS
    pane
    0.31
    iture
    0.30
    á»ģu
    0.28
    romo
    0.27
    æ´»
    0.27
    arro
    0.27
    frared
    0.26
    agan
    0.26
    iration
    0.26
    ishes
    0.26
    Activations Density 0.882%

    No Known Activations