© 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. 27-TRANSCODER-HP
    7. 9278
    Prev
    Next
    INDEX
    Explanations

    minimize

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ught
    -0.28
     Require
    -0.25
     Peg
    -0.24
    Pad
    -0.24
    Require
    -0.24
    ought
    -0.23
    .getModel
    -0.23
    ä¸Ģç¬ij
    -0.23
    globals
    -0.23
    æ¼Ķèīº
    -0.22
    POSITIVE LOGITS
    伤害
    0.32
    æĥħåĨµä¸ĭ
    0.31
     harm
    0.30
     societal
    0.28
     interference
    0.28
    好å¤Ħ
    0.27
     fal
    0.27
    åĽłæŀľ
    0.27
     damage
    0.27
     causal
    0.26
    Activations Density 0.017%

    No Known Activations