© 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. 112180
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    åĽĽå¹´
    -0.28
    è¿Ļç§įæĸ¹å¼ı
    -0.26
    笳
    -0.25
    çģ«çĤ¬
    -0.25
    è¿ľç¦»
    -0.24
    åĢŁåĬ©
    -0.24
    æĸ¹å¼ı
    -0.23
    åı¦æľī
    -0.23
    æĪIJ
    -0.23
    лÑİ
    -0.23
    POSITIVE LOGITS
    otomy
    0.26
    PURE
    0.25
    igos
    0.25
    aked
    0.24
    éĻ¢åī¯éĻ¢éķ¿
    0.24
    inen
    0.24
    á»ĩnh
    0.24
     Morm
    0.24
    oids
    0.23
    UTDOWN
    0.23
    Activations Density 0.008%

    No Known Activations