© 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. 22-TRANSCODER-HP
    7. 87670
    Prev
    Next
    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    认为
    -0.32
    èªįçĤº
    -0.29
    raph
    -0.28
    ONENT
    -0.28
    æķ´çIJĨ
    -0.27
    é¢ĩæľī
    -0.27
    İ·
    -0.27
    programming
    -0.27
    toi
    -0.26
    helm
    -0.26
    POSITIVE LOGITS
     telling
    0.25
    ajs
    0.25
    åľ°æ®µ
    0.25
    è¿Ŀ约
    0.25
     faces
    0.24
     face
    0.23
     grip
    0.23
    éĶ¦æłĩ
    0.23
     fra
    0.23
     nag
    0.23
    Activations Density 0.028%

    No Known Activations