© 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. 40272
    Prev
    Next
    INDEX
    Explanations

    Names and abbreviations

    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
     Roman
    -0.72
    Roman
    -0.70
    ç½Ĺ马
    -0.68
    IAN
    -0.66
     roman
    -0.65
    ian
    -0.63
    roman
    -0.58
     ROM
    -0.58
    iana
    -0.56
    ians
    -0.55
    POSITIVE LOGITS
     nx
    0.30
     Cu
    0.29
    esub
    0.27
     Le
    0.27
     Colleg
    0.27
     Po
    0.27
     cu
    0.27
     Antar
    0.27
     Cent
    0.26
    ewn
    0.26
    Activations Density 4.397%

    No Known Activations