© 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. 88436
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Gates
    -0.28
    finally
    -0.28
    ýt
    -0.27
    %A
    -0.27
     GW
    -0.27
     finally
    -0.26
    JK
    -0.25
    ç»ĵåIJĪ
    -0.24
    æħİ
    -0.24
     Wash
    -0.24
    POSITIVE LOGITS
    ãĥĽãĥ¼ãĥł
    0.28
    家å±ħ
    0.27
     home
    0.26
     uns
    0.26
    mund
    0.26
    asily
    0.26
    ival
    0.25
    whel
    0.25
    羸
    0.25
    uns
    0.25
    Activations Density 0.005%

    No Known Activations