© 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. 97568
    Prev
    Next
    INDEX
    Explanations

    Photo captions/descriptions

    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
    .tail
    -0.28
     stehen
    -0.26
    -produ
    -0.24
    èĬĻ
    -0.23
    .keras
    -0.23
    iad
    -0.23
    çĸ¾
    -0.23
    itty
    -0.23
    itia
    -0.23
    ymmetric
    -0.23
    POSITIVE LOGITS
    ä¼łçľŁ
    0.24
     said
    0.23
     Afr
    0.23
    (OP
    0.23
    Source
    0.23
    /or
    0.23
     refined
    0.23
    çıįæĥľ
    0.23
     excursion
    0.23
     IPS
    0.22
    Activations Density 0.006%

    No Known Activations