© 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. 42209
    Prev
    Next
    INDEX
    Explanations

    Virginia locations

    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
    èĤĭ
    -0.29
    panse
    -0.29
    rlen
    -0.28
    解æĶ¾æĢĿæĥ³
    -0.28
    (IB
    -0.26
    elib
    -0.26
    wing
    -0.24
    nesia
    -0.24
    dob
    -0.24
    zee
    -0.24
    POSITIVE LOGITS
    Va
    0.28
     viet
    0.28
    VC
    0.28
    VL
    0.27
    äºĶ
    0.27
    çĤī
    0.26
    umn
    0.26
    VA
    0.26
     Kron
    0.26
    วà¸Ļ
    0.26
    Activations Density 0.006%

    No Known Activations