© 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. 108352
    Prev
    Next
    INDEX
    Explanations

    statistics and proportions

    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
    åĽĽé¡¹
    -0.31
    æĬij
    -0.29
    åħ±
    -0.28
    两项
    -0.28
     priorities
    -0.28
     Priority
    -0.26
    EFF
    -0.26
    prior
    -0.26
    ä¼ĺåħĪ
    -0.26
    两ç§į
    -0.26
    POSITIVE LOGITS
    LIB
    0.30
    lib
    0.28
    åŃĺ
    0.26
     lif
    0.26
    rlen
    0.25
     liber
    0.25
    ograph
    0.25
    룸
    0.24
     Stephan
    0.24
     pitch
    0.24
    Activations Density 0.124%

    No Known Activations