© 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. 57274
    Prev
    Next
    INDEX
    Explanations

    code and tokens

    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
     Raw
    -0.29
     floors
    -0.28
     raw
    -0.28
    stab
    -0.28
    æĦŁ
    -0.27
    _RAW
    -0.26
    	raw
    -0.26
     RAW
    -0.25
    .Raw
    -0.25
    cÃŃ
    -0.25
    POSITIVE LOGITS
    belongs
    0.29
    æĿĥåĪ©
    0.28
    æĿĥéĻIJ
    0.27
    ç»ĨèĬĤ
    0.27
    ).__
    0.27
    éĻĦ件
    0.26
    çļĦæĿĥåĪ©
    0.26
    æĥħ
    0.26
    æ³ķè§Ħ
    0.25
    modern
    0.25
    Activations Density 0.004%

    No Known Activations