© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98895
    Prev
    Next
    INDEX
    Explanations

    Im

    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
    RICT
    -0.28
    ÏĤ
    -0.26
    /UI
    -0.26
     RR
    -0.25
    /IP
    -0.25
    ÑĭÑĪ
    -0.24
    евиÑĩ
    -0.24
     Train
    -0.23
    TRIES
    -0.23
    itic
    -0.23
    POSITIVE LOGITS
    adem
    0.30
    ply
    0.25
    antha
    0.25
    igrams
    0.25
    ä¹IJ
    0.25
    dest
    0.25
    ason
    0.25
    agination
    0.24
    iquid
    0.24
    äºĮ人
    0.24
    Activations Density 0.316%

    No Known Activations