© 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. 129317
    Prev
    Next
    INDEX
    Explanations

    we

    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
    éĢļ常
    -0.30
    æĻ®éģį
    -0.30
    (exports
    -0.29
    åŁºæľ¬åİŁåĪĻ
    -0.27
    çIJĥè¿·
    -0.27
    æķĻä¼ļ
    -0.27
     usual
    -0.26
    å¾Ģå¾Ģä¼ļ
    -0.26
    rum
    -0.25
    èĮĥçķ´
    -0.25
    POSITIVE LOGITS
    iasi
    0.27
     success
    0.27
     unc
    0.26
     grounding
    0.26
     impl
    0.26
    à¦Ļ
    0.25
    imp
    0.24
     Impl
    0.24
    rolling
    0.24
     деÑĢ
    0.23
    Activations Density 0.003%

    No Known Activations