© 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. 32-TRANSCODER-HP
    7. 42851
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nf
    -0.28
    istique
    -0.25
     Jah
    -0.25
    ä¸įä¸ĭ
    -0.25
    使人
    -0.24
     nf
    -0.24
     Sof
    -0.24
     pdu
    -0.24
     nos
    -0.24
    .getClient
    -0.24
    POSITIVE LOGITS
    steen
    0.27
     sink
    0.27
    æĭĶ
    0.25
    fc
    0.24
     Fibonacci
    0.24
    çIJĨæĥ³ä¿¡å¿µ
    0.24
    VV
    0.24
    ç¼¢
    0.24
     Active
    0.24
    sal
    0.23
    Activations Density 0.007%

    No Known Activations