© 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. 42383
    Prev
    Next
    INDEX
    Explanations

    say "ent" ending

    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
    ites
    -0.35
    ite
    -0.31
    齡
    -0.30
    ForMember
    -0.28
    à¸Ħà¸Ń
    -0.28
    atab
    -0.28
    itr
    -0.27
    иÑĤа
    -0.27
    ita
    -0.26
    -h
    -0.26
    POSITIVE LOGITS
    èĦī
    0.29
    alers
    0.27
    ä»·ä½į
    0.25
    pulse
    0.25
    æ¨¡æł·
    0.25
    è¿Ļå¼ł
    0.24
    arkan
    0.24
    èĴĤ
    0.24
    åij½è¿IJ
    0.24
    apas
    0.24
    Activations Density 0.003%

    No Known Activations