© 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. 108713
    Prev
    Next
    INDEX
    Explanations

    Liability disclaimers

    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
    éĥ½åľ¨
    -0.28
    ellar
    -0.27
    èĥ½å¤Łåľ¨
    -0.26
    çģ¾éļ¾
    -0.26
    stacle
    -0.25
    plug
    -0.24
    éĢ¢
    -0.24
     sensitivity
    -0.24
    æķıæĦŁ
    -0.24
     trot
    -0.24
    POSITIVE LOGITS
    ë¡ł
    0.28
    erview
    0.28
    缸符
    0.26
     yapılan
    0.26
    lagen
    0.26
    åĮ¹éħį
    0.25
    qui
    0.25
    ãģĤãĤĬãģ¾ãģĻãģĮ
    0.25
    /Public
    0.24
    oria
    0.24
    Activations Density 0.023%

    No Known Activations