© 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. 98617
    Prev
    Next
    INDEX
    Explanations

    flying

    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
     Âł
    -0.34
     ...č↵
    -0.29
    ³³³³
    -0.29
    î
    -0.29
     ...)
    -0.26
    ³³³³³³³³
    -0.26
     Âł Âł Âł Âł
    -0.25
    ³³³³³³³
    -0.25
    ³³³
    -0.24
     Âł Âł
    -0.24
    POSITIVE LOGITS
     ðŁĺī
    0.23
    hone
    0.22
    LB
    0.22
    æĪĹ
    0.21
    åµĺ
    0.21
    etal
    0.21
     BI
    0.21
    eyed
    0.20
    ÅĽcie
    0.20
    æĤĶ
    0.20
    Activations Density 0.029%

    No Known Activations