© 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. 22-TRANSCODER-HP
    7. 130748
    Prev
    Next
    INDEX
    Explanations

    issue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ĥæĢĿ
    -0.27
    itioner
    -0.27
    æ·±å¤Ħ
    -0.26
    nett
    -0.26
    _interfaces
    -0.25
    çļĦåĬªåĬĽ
    -0.25
     metic
    -0.25
    å°½åĬĽ
    -0.25
    sembler
    -0.25
    lations
    -0.25
    POSITIVE LOGITS
    ej
    0.28
    eri
    0.27
    ances
    0.25
     constitution
    0.25
     beam
    0.24
    ä»Ģä¹Īæł·çļĦ
    0.24
    ead
    0.24
    ç»Ļ
    0.24
    ìĭł
    0.23
    å¼ĢåĬŀ
    0.23
    Activations Density 0.089%

    No Known Activations