© 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. 87765
    Prev
    Next
    INDEX
    Explanations

    up

    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
     contrasts
    -0.27
    ä¸įæŃ¢
    -0.25
    inary
    -0.24
    igli
    -0.24
     deferred
    -0.24
     able
    -0.24
    istica
    -0.24
    idot
    -0.24
    nist
    -0.24
    çģ¿çĥĤ
    -0.24
    POSITIVE LOGITS
    åĩıå°ij
    0.28
    åĵ¥
    0.27
     Revolution
    0.26
     twig
    0.26
    åĩıå°ijäºĨ
    0.26
    缩å°ı
    0.26
    çı¥
    0.25
    Css
    0.25
    åĩıåħį
    0.25
    oucher
    0.25
    Activations Density 0.002%

    No Known Activations