© 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. 97565
    Prev
    Next
    INDEX
    Explanations

    Cause and effect

    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
    _OPERATION
    -0.27
    åħļå·¥å§Ķ
    -0.26
    éĢĢ
    -0.25
    _contents
    -0.25
    çļĦçĪ¶äº²
    -0.24
    ãĤ·ãĥ§
    -0.24
     Mann
    -0.24
    fad
    -0.24
    Credits
    -0.23
     randomNumber
    -0.23
    POSITIVE LOGITS
    utes
    0.27
    STONE
    0.27
    ecer
    0.27
    vt
    0.26
    antly
    0.26
    étique
    0.25
    å¾®å¦Ļ
    0.25
    ະ
    0.24
    eline
    0.23
     misc
    0.23
    Activations Density 0.014%

    No Known Activations