© 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. 43834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    arov
    -0.29
    ATALOG
    -0.26
    extr
    -0.26
     sublic
    -0.25
    __((
    -0.25
    |(
    -0.25
     Marcus
    -0.25
    ANEL
    -0.25
     Mental
    -0.24
    .nl
    -0.24
    POSITIVE LOGITS
    rem
    0.28
    æıIJéĨĴ
    0.26
    REM
    0.25
    æĥĬå¥ĩ
    0.25
     Correction
    0.25
    磫æŃ£
    0.25
     Fälle
    0.25
     backups
    0.25
    Cases
    0.25
     tub
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.