© 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. 111674
    Prev
    Next
    INDEX
    Explanations

    future

    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
    ho
    -0.29
    mites
    -0.25
    .rs
    -0.25
    ä¼Ĭæĸ¯
    -0.24
    allo
    -0.24
    ensem
    -0.24
     palms
    -0.24
    orges
    -0.24
    IRO
    -0.24
     wholes
    -0.24
    POSITIVE LOGITS
    ierre
    0.29
    ergus
    0.28
    ReadOnly
    0.26
    æ¶īåıĬåĪ°
    0.25
    nad
    0.25
    ноп
    0.25
     ↵
    0.25
     Identification
    0.24
    t
    0.24
     "]"
    0.24
    Activations Density 0.012%

    No Known Activations