© 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. 35-TRANSCODER-HP
    7. 39307
    Prev
    Next
    INDEX
    Explanations

    legal, locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    POR
    -0.32
     blowing
    -0.27
     Cald
    -0.26
    _vi
    -0.25
     vamos
    -0.25
    åĬĥ
    -0.24
    大éĩıçļĦ
    -0.24
     bil
    -0.24
     vertex
    -0.23
     namespace
    -0.23
    POSITIVE LOGITS
    que
    0.30
    se
    0.30
    ç»ĵ
    0.29
    eing
    0.29
    eee
    0.28
    eeee
    0.28
    ts
    0.28
    tech
    0.28
    eous
    0.28
    overn
    0.28
    Activations Density 7.919%

    No Known Activations