© 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. 108445
    Prev
    Next
    INDEX
    Explanations

    Beginning of documents

    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
    çĵ®
    -0.31
    æħµ
    -0.30
    æĺ¯éĿŀ
    -0.26
    ä¸Ģåī¯
    -0.25
    åĵij
    -0.25
    .setFocus
    -0.24
    eam
    -0.24
    åħĪè¿ĽæĬĢæľ¯
    -0.24
    å¦Ĵ
    -0.23
    .param
    -0.23
    POSITIVE LOGITS
    åĿĬ
    0.28
    ITIES
    0.27
    æıIJ示
    0.25
    opher
    0.25
    ä¸Ģéģį
    0.25
     contexts
    0.24
    çľģ
    0.24
    .Other
    0.24
    icity
    0.24
     elsewhere
    0.24
    Activations Density 0.917%

    No Known Activations