© 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. 98367
    Prev
    Next
    INDEX
    Explanations

    of

    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
    atan
    -0.28
    she
    -0.26
    immune
    -0.26
     Proposal
    -0.26
    heet
    -0.26
    ಶ
    -0.25
    proposal
    -0.25
    {:
    -0.25
     McMaster
    -0.25
     Riding
    -0.24
    POSITIVE LOGITS
    湿
    0.28
    osex
    0.25
    itet
    0.25
    æ¿ķ
    0.24
    çĶ¸
    0.24
     amet
    0.24
    vore
    0.24
    ä¸į让
    0.23
    onation
    0.23
    nı
    0.23
    Activations Density 0.007%

    No Known Activations