© 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. 41973
    Prev
    Next
    INDEX
    Explanations

    Code and legal documents

    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
    Clients
    -0.32
    âĮĤ
    -0.28
     clients
    -0.28
    омеÑĢ
    -0.27
    getClient
    -0.26
    _clients
    -0.26
    uci
    -0.26
     getClient
    -0.26
    aster
    -0.25
    gf
    -0.25
    POSITIVE LOGITS
    举
    0.27
    åIJİåı°
    0.26
    vet
    0.26
    Side
    0.26
    åī¯æĢ»
    0.26
    aux
    0.25
    èħ°
    0.25
     sinks
    0.25
    SIDE
    0.25
    æīĵ
    0.24
    Activations Density 0.003%

    No Known Activations