© 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. 87980
    Prev
    Next
    INDEX
    Explanations

    commonality

    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
    omite
    -0.30
    éĹ®é¢ĺæĺ¯
    -0.29
    scribe
    -0.29
    ething
    -0.28
    å¿ĥèĦıçĹħ
    -0.27
    çļĦ身ä½ĵ
    -0.26
    esk
    -0.25
    CHandle
    -0.25
    scription
    -0.25
    Intensity
    -0.25
    POSITIVE LOGITS
    ref
    0.31
     in
    0.30
     global
    0.28
    ins
    0.28
     ins
    0.25
    rome
    0.25
     across
    0.24
     Ref
    0.24
    In
    0.24
     societal
    0.24
    Activations Density 0.022%

    No Known Activations