© 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. 111819
    Prev
    Next
    INDEX
    Explanations

    qu

    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
     productList
    -0.28
    Contracts
    -0.26
    ONEY
    -0.25
    ä¸Ńè¶ħ
    -0.25
    æĪĺåľºä¸Ĭ
    -0.25
     contracted
    -0.24
    contract
    -0.24
    ç»Ī身
    -0.24
    çŁĽçĽ¾
    -0.24
     contract
    -0.24
    POSITIVE LOGITS
     refurb
    0.28
    mania
    0.28
    -me
    0.25
    /apt
    0.24
     ÐľÐµ
    0.24
     cref
    0.24
    stück
    0.24
    lington
    0.24
    ogne
    0.24
    loops
    0.24
    Activations Density 0.008%

    No Known Activations