© 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. 98876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Pill
    -0.29
    桨
    -0.28
    åŀĭ
    -0.27
    ered
    -0.27
     type
    -0.26
     gridSize
    -0.26
     tw
    -0.26
     responsible
    -0.25
    sm
    -0.24
     zip
    -0.24
    POSITIVE LOGITS
    }catch
    0.28
    æłĩéħį
    0.27
    ä¹ĭ家
    0.25
     Madness
    0.25
    è°ĥçIJĨ
    0.25
     tả
    0.25
    SWG
    0.24
     Featured
    0.24
    ublic
    0.24
    èķĥ
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.