© 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. 24-TRANSCODER-HP
    7. 150205
    Prev
    Next
    INDEX
    Explanations

    itch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĽĿåħī
    -0.32
    æµģ
    -0.29
    éĢł
    -0.28
    ill
    -0.28
    èĬĤ
    -0.28
    ilt
    -0.27
    è¹ī
    -0.27
    çīĮ
    -0.27
    å¤ĸåĽ´
    -0.25
    éĴŁ
    -0.25
    POSITIVE LOGITS
    å±İ
    0.30
    çű
    0.27
    åıijå±ķ模å¼ı
    0.24
    ermint
    0.24
    .Pointer
    0.24
    çªģå¦Ĥ
    0.24
    樾
    0.23
    chw
    0.23
     bother
    0.23
    RefPtr
    0.23
    Activations Density 1.286%

    No Known Activations