© 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. 25-TRANSCODER-HP
    7. 109016
    Prev
    Next
    INDEX
    Explanations

    technical/uncommon language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Capt
    -0.31
     caption
    -0.28
     formal
    -0.28
     formally
    -0.27
    åIJ¬å®Į
    -0.27
     captured
    -0.27
     Caption
    -0.26
    丰
    -0.26
    å¤įæŁ¥
    -0.25
    nung
    -0.25
    POSITIVE LOGITS
    WebRequest
    0.27
    æľĭ
    0.27
    getRepository
    0.25
    гоÑĢод
    0.24
    illage
    0.24
    whereIn
    0.24
    æįŁå®³
    0.24
    æł¡åĽŃ
    0.24
    èģĶç½ij
    0.24
    éĻ·
    0.24
    Activations Density 0.911%

    No Known Activations