© 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. 41951
    Prev
    Next
    INDEX
    Explanations

    <

    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
    igan
    -0.28
    eme
    -0.28
     trackers
    -0.27
     tracker
    -0.26
     Canonical
    -0.26
    snapshot
    -0.26
    æľºæ¢°åĮĸ
    -0.26
     snapshot
    -0.26
    иÑĤел
    -0.25
    hone
    -0.25
    POSITIVE LOGITS
    pras
    0.26
    åĬłçĽĸ
    0.25
    ovy
    0.25
    è¾ĵ
    0.25
    sts
    0.24
    cient
    0.24
    IVED
    0.24
    çİ°è¡Į
    0.24
    etta
    0.23
    memo
    0.23
    Activations Density 0.001%

    No Known Activations