© 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. 24-TRANSCODER-HP
    7. 150023
    Prev
    Next
    INDEX
    Explanations

    To

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为äºĨ
    -0.31
    为äºĨ让
    -0.28
    çĤºäºĨ
    -0.28
    cheng
    -0.27
    urge
    -0.25
    lyph
    -0.25
    rut
    -0.25
    ewater
    -0.24
    rub
    -0.24
    )(_
    -0.24
    POSITIVE LOGITS
     shall
    0.29
     these
    0.29
     this
    0.27
     å±
    0.25
    DO
    0.25
    id
    0.25
    iku
    0.25
    ×Ļ׼
    0.24
    è¿ĺä¼ļ
    0.24
    éļĶ离
    0.24
    Activations Density 1.142%

    No Known Activations