© 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. 32-TRANSCODER-HP
    7. 43134
    Prev
    Next
    INDEX
    Explanations

    future

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yours
    -0.31
     tÆ°á»Ŀng
    -0.28
     esac
    -0.26
    urat
    -0.26
    etting
    -0.26
    ç»Ļä½ł
    -0.25
    ÃŃg
    -0.25
    asa
    -0.25
     tand
    -0.24
    ½Ķ
    -0.24
    POSITIVE LOGITS
     scenario
    0.31
     look
    0.31
    éĺ´éĺ³
    0.30
    ernity
    0.28
     vision
    0.28
     role
    0.28
    lä
    0.28
    æĺİæľĹ
    0.27
    Look
    0.27
     trajectory
    0.27
    Activations Density 0.004%

    No Known Activations