© 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. 88000
    Prev
    Next
    INDEX
    Explanations

    Comparisons and degree

    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
     ÃĤu
    -0.28
    WithTag
    -0.26
    addons
    -0.26
    bew
    -0.26
    ÑĴ
    -0.25
    æł¸æŁ¥
    -0.24
    ä¸įå½ĵ
    -0.24
     aimed
    -0.24
    .pageX
    -0.24
    itä
    -0.23
    POSITIVE LOGITS
     possible
    0.40
     possÃŃvel
    0.33
     Constraints
    0.31
     Possible
    0.31
    possible
    0.31
    æīĢèĥ½
    0.30
    _possible
    0.29
    Possible
    0.29
     constrained
    0.28
    辦æ³ķ
    0.28
    Activations Density 0.023%

    No Known Activations