© 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. 107639
    Prev
    Next
    INDEX
    Explanations

    position

    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
    actic
    -0.26
    [,]
    -0.24
    afe
    -0.24
    liche
    -0.24
    ами
    -0.24
    acle
    -0.24
    ãģ§ãģį
    -0.23
    '[
    -0.23
    çļĦéĢīæĭ©
    -0.23
    à¹ģสà¸Ķà¸ĩ
    -0.23
    POSITIVE LOGITS
    æłī
    0.27
    imuth
    0.27
    èĥŀ
    0.26
    ç»İ
    0.26
    raft
    0.26
    ragen
    0.25
     beaten
    0.25
    nock
    0.24
    scription
    0.24
    erate
    0.24
    Activations Density 0.976%

    No Known Activations