© 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. 42337
    Prev
    Next
    INDEX
    Explanations

    pro

    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
    ANCE
    -0.29
    atively
    -0.26
    ableObject
    -0.26
    odial
    -0.26
    ively
    -0.25
    ä½½
    -0.25
    oble
    -0.25
    AREN
    -0.24
    uur
    -0.24
    ABLE
    -0.23
    POSITIVE LOGITS
    anut
    0.28
    cket
    0.28
    kur
    0.26
    æī¿
    0.26
    äºĴ
    0.25
     cess
    0.25
    \Auth
    0.25
    çĶľèľľ
    0.25
     mutated
    0.25
    tection
    0.25
    Activations Density 0.031%

    No Known Activations