© 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. 88451
    Prev
    Next
    INDEX
    Explanations

    Saying/Stating

    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
    purpose
    -0.28
     academics
    -0.26
    ãĥ³ãĤ°
    -0.26
     purpose
    -0.25
     gÅĤówne
    -0.24
    .getLong
    -0.24
     Biggest
    -0.24
    $core
    -0.24
    -wing
    -0.23
    -screen
    -0.23
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.29
    çIJĨæĥ³çļĦ
    0.29
    idelity
    0.28
    è¿ĻçĤ¹
    0.26
    è¿Ļæł·æīįèĥ½
    0.26
    ä»ĸèĩªå·±
    0.25
     saving
    0.25
    ANTE
    0.25
    ):
    0.25
    éĢĢ
    0.24
    Activations Density 0.008%

    No Known Activations