© 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. 87178
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    asar
    -0.28
    åĪĴ
    -0.27
    =np
    -0.26
    _np
    -0.24
    åŃĺ
    -0.24
     commission
    -0.23
     commissions
    -0.23
    ismo
    -0.23
     zg
    -0.23
     zd
    -0.23
    POSITIVE LOGITS
    alten
    0.27
    _INLINE
    0.26
     Southampton
    0.25
    utive
    0.24
    verte
    0.24
    æĽ´å¤ļä¿¡æģ¯
    0.24
    INED
    0.24
    SCRIBE
    0.24
    roduce
    0.23
    phans
    0.23
    Activations Density 0.012%

    No Known Activations