© 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. 41367
    Prev
    Next
    INDEX
    Explanations

    legal documents or software code

    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
     Crate
    -0.30
    ROL
    -0.29
    (TIM
    -0.28
    (SS
    -0.28
    (rv
    -0.27
    (Py
    -0.26
    dge
    -0.26
    adol
    -0.26
    cobra
    -0.26
     resil
    -0.25
    POSITIVE LOGITS
    opsis
    0.28
    _
    0.27
     setSupportActionBar
    0.27
     firsthand
    0.26
    éĺĬ
    0.25
    .GetCurrentMethod
    0.25
     quelque
    0.25
    AlgorithmException
    0.24
    0.24
    ifice
    0.24
    Activations Density 0.030%

    No Known Activations