© 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. 39766
    Prev
    Next
    INDEX
    Explanations

    technical language

    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
    isa
    -0.32
    ded
    -0.32
    anan
    -0.29
    issa
    -0.28
    ately
    -0.28
    iso
    -0.27
    asc
    -0.27
    изаÑĨиÑı
    -0.26
    astes
    -0.26
    AST
    -0.26
    POSITIVE LOGITS
     CT
    0.29
    vero
    0.28
    ct
    0.27
    对ä¸įèµ·
    0.27
     ct
    0.26
    verb
    0.26
    _CT
    0.26
    åĽŀå½Ĵ
    0.26
    CT
    0.26
     Drawer
    0.26
    Activations Density 0.817%

    No Known Activations