© 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. 112083
    Prev
    Next
    INDEX
    Explanations

    lesson

    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
    ики
    -0.31
    -floor
    -0.26
    æľīåħ´è¶£
    -0.26
    è½®
    -0.25
     improving
    -0.25
     speakers
    -0.25
     structured
    -0.24
     floor
    -0.24
    å·¡éĢ»
    -0.24
    éĿŀ常éĢĤåIJĪ
    -0.24
    POSITIVE LOGITS
    ercul
    0.33
    åľ©
    0.26
    essay
    0.25
    çļĦ说æ³ķ
    0.25
     discredit
    0.25
    elix
    0.25
    ammen
    0.24
    arkin
    0.23
    ombre
    0.23
     Toggle
    0.23
    Activations Density 0.014%

    No Known Activations