© 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. 25-TRANSCODER-HP
    7. 107352
    Prev
    Next
    INDEX
    Explanations

    blockage/obstruction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¥çļĦ
    -0.32
    ç»Ļä»ĸ们
    -0.29
    éĻªçĿĢ
    -0.28
    ä¸ªé¡¹çĽ®
    -0.27
    大家åĪĨ享
    -0.26
    便ä¼ļ
    -0.25
    endregion
    -0.24
    ç»Ļ大家
    -0.24
    ahkan
    -0.24
     ^↵
    -0.24
    POSITIVE LOGITS
    ation
    0.30
    ting
    0.30
    ing
    0.30
    ism
    0.28
    age
    0.27
     statistically
    0.27
    oids
    0.27
     Dere
    0.27
    ache
    0.27
    ivity
    0.26
    Activations Density 0.114%

    No Known Activations