© 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. 108065
    Prev
    Next
    INDEX
    Explanations

    Code and documentation excerpts

    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
    åĪĨè¡Į
    -0.26
    èĥ½ä½¿
    -0.25
     Babe
    -0.24
    rical
    -0.24
    ramework
    -0.24
    affected
    -0.24
    çļĦåľ°åĽ¾
    -0.24
    使
    -0.23
    anzi
    -0.23
    instr
    -0.23
    POSITIVE LOGITS
    Lazy
    0.29
    è¿Ļæľ¬ä¹¦
    0.28
     Lazy
    0.26
     Mel
    0.26
     guys
    0.26
    客æ°Ķ
    0.26
    estead
    0.25
     Sel
    0.25
     Raw
    0.25
     Kevin
    0.24
    Activations Density 0.948%

    No Known Activations