© 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. 129686
    Prev
    Next
    INDEX
    Explanations

    Statistics

    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
    ¯¯¯¯
    -0.29
    gang
    -0.28
    imony
    -0.26
    peria
    -0.26
    ogi
    -0.26
    (Page
    -0.25
    PP
    -0.25
    reau
    -0.24
     PP
    -0.24
    rü
    -0.24
    POSITIVE LOGITS
    Caller
    0.24
    ãĤ¢ãĤ¦ãĥĪ
    0.24
    éĤ£ä¸ĢåĪ»
    0.24
    nearest
    0.24
    getConfig
    0.23
    leep
    0.23
    梦
    0.23
    é»ĦåŁĶ
    0.22
     nearest
    0.22
    ascular
    0.22
    Activations Density 0.005%

    No Known Activations