© 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. 112541
    Prev
    Next
    INDEX
    Explanations

    technical questions and answers

    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
    ModelError
    -0.28
    åħ¶å®ĥéĹ®é¢ĺ
    -0.28
    æľ¬ç½ij
    -0.28
    cripcion
    -0.26
     defaulted
    -0.25
     Mathf
    -0.24
    æŃ£æĸĩ
    -0.24
    è´¼
    -0.24
    ä»ĸ表示
    -0.24
    该éĻ¢
    -0.24
    POSITIVE LOGITS
    appe
    0.30
    æľīåºı
    0.27
     indiv
    0.27
    å¾ģ
    0.25
    æ±Łå±±
    0.25
    IBLE
    0.25
    æģº
    0.25
     emerg
    0.24
    loh
    0.24
    森
    0.24
    Activations Density 0.272%

    No Known Activations