© 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. 129208
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Above
    -0.30
     Above
    -0.26
    amel
    -0.26
     above
    -0.25
    unlikely
    -0.25
    ên
    -0.24
    Boundary
    -0.24
    Liter
    -0.24
    Own
    -0.24
    éŨçªĹ
    -0.24
    POSITIVE LOGITS
    leck
    0.29
    çļĦæľīæķĪ
    0.26
    aked
    0.26
    \V
    0.25
     Victor
    0.25
     divor
    0.24
    omed
    0.24
    è¤Ĵ
    0.24
    :expr
    0.24
     Sno
    0.24
    Activations Density 0.005%

    No Known Activations