© 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. 31-TRANSCODER-HP
    7. 18754
    Prev
    Next
    INDEX
    Explanations

    kind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ains
    -0.27
    ises
    -0.26
    ise
    -0.26
    /lists
    -0.26
    ieres
    -0.25
    大å®Ĺ
    -0.25
    acist
    -0.24
     ull
    -0.24
     imbalance
    -0.24
     Toledo
    -0.24
    POSITIVE LOGITS
    gp
    0.29
    å°ĺ
    0.27
    éĻĤ
    0.26
    ÑģÑĤаÑĤ
    0.26
    wp
    0.26
    西åįĹ
    0.26
    redd
    0.26
    nostic
    0.26
    åĬ¨æľº
    0.25
    婧
    0.25
    Activations Density 0.009%

    No Known Activations