© 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. 18596
    Prev
    Next
    INDEX
    Explanations

    Che

    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
    ifest
    -0.28
     format
    -0.27
    fest
    -0.26
    ãĥIJãĤ¤
    -0.25
    ledo
    -0.25
    ements
    -0.25
    èĻ¬
    -0.25
    èijº
    -0.25
    -Token
    -0.24
    ä¹ĥ
    -0.24
    POSITIVE LOGITS
     IDisposable
    0.25
    keh
    0.25
    ãĥŀãĥ¼
    0.25
     convinced
    0.24
    weak
    0.24
     polym
    0.24
     Freem
    0.24
     weak
    0.24
    èĸĦå¼±
    0.23
    ait
    0.23
    Activations Density 0.002%

    No Known Activations