© 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. 23-TRANSCODER-HP
    7. 24115
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ´¾
    -0.32
    å¢ī
    -0.31
    parts
    -0.29
    edList
    -0.29
     identities
    -0.28
    bre
    -0.24
     local
    -0.24
     Dyn
    -0.24
    ç»İ
    -0.24
    flow
    -0.24
    POSITIVE LOGITS
     iÅŁaret
    0.29
    lingen
    0.28
    arta
    0.27
    iego
    0.26
    åĤ¬çĶŁ
    0.26
     Executive
    0.26
    cobra
    0.26
     engulf
    0.25
    åľ¨å¤ĸ
    0.25
    å°ĨåĨĽ
    0.24
    Activations Density 0.006%

    No Known Activations