© 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. 112443
    Prev
    Next
    INDEX
    Explanations

    programming 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
    è´¢
    -0.28
     '!
    -0.26
    ç¿İ
    -0.26
    lemen
    -0.25
    èĬ±éĴ±
    -0.25
    禾
    -0.25
    æħĪ
    -0.24
    mir
    -0.23
     ocas
    -0.23
    icularly
    -0.23
    POSITIVE LOGITS
    -inline
    0.28
    ente
    0.27
    enty
    0.27
    globals
    0.27
    ilot
    0.27
    fone
    0.26
    ä¸Ģçľĭ
    0.26
    tern
    0.25
     contempor
    0.25
    Zend
    0.25
    Activations Density 0.007%

    No Known Activations