© 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. 30-TRANSCODER-HP
    7. 96689
    Prev
    Next
    INDEX
    Explanations

    Ab

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    um
    -0.27
    wards
    -0.26
    allax
    -0.26
    éĩĬæĶ¾
    -0.25
    oph
    -0.25
     link
    -0.25
     parallel
    -0.24
    Ñĥм
    -0.24
     ctype
    -0.24
    serter
    -0.24
    POSITIVE LOGITS
    å´´
    0.27
    ernel
    0.27
    пÑĤ
    0.26
    ingly
    0.26
    ernal
    0.25
    SAT
    0.25
    éĻ¢åŃIJ
    0.25
    åŀ£
    0.24
    GLE
    0.24
     Dome
    0.24
    Activations Density 0.883%

    No Known Activations