© 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. 98419
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    äºĮ级
    -0.28
    åĪĹåħ¥
    -0.27
    æĦıè§ģåıįé¦Ī
    -0.25
    æĭ¿åĩº
    -0.25
    éĤ£äºĽ
    -0.25
    erner
    -0.25
    æĬĬè¿Ļ个
    -0.25
    à¸łà¸²à¸¢
    -0.25
    vy
    -0.25
    æĥħèĬĤ
    -0.24
    POSITIVE LOGITS
    çĵľ
    0.28
     PED
    0.28
    ResponseBody
    0.26
    blind
    0.26
    æľĭåıĭåľĪ
    0.25
    atures
    0.25
    itsu
    0.24
    edo
    0.24
    ecessarily
    0.24
    lett
    0.24
    Activations Density 0.011%

    No Known Activations