© 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. 87784
    Prev
    Next
    INDEX
    Explanations

    suitable

    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
    æĥ³æ³ķ
    -0.25
     STATES
    -0.24
    asive
    -0.24
    æĪªæŃ¢
    -0.24
     pains
    -0.23
    å¾Īæĥ³
    -0.23
     kurs
    -0.23
     interes
    -0.23
    æĢ¥
    -0.23
     flat
    -0.23
    POSITIVE LOGITS
    çłĶ讨
    0.29
    çĶ¨æĿ¥
    0.26
     battleground
    0.26
    èĦ¾èĥĥ
    0.25
    dogs
    0.25
    oÄŁ
    0.24
     Genius
    0.24
    è¿·ä¿¡
    0.24
    llib
    0.24
    çĶ¨äºİ
    0.24
    Activations Density 0.022%

    No Known Activations