© 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. 108388
    Prev
    Next
    INDEX
    Explanations

    code

    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
    æĢ§åij½
    -0.31
    å±Ģ
    -0.28
     condition
    -0.27
    åİ¿åħ¬å®īå±Ģ
    -0.27
    ous
    -0.27
    æ³Ľ
    -0.27
    uth
    -0.27
    (async
    -0.25
     ich
    -0.24
     generalize
    -0.24
    POSITIVE LOGITS
    assed
    0.28
    azu
    0.27
    пÑĤ
    0.25
    èĴ¯
    0.25
    并ä¸įä¼ļ
    0.25
    adians
    0.25
     вмеÑģÑĤ
    0.25
    pedo
    0.24
    uze
    0.24
    zew
    0.24
    Activations Density 0.137%

    No Known Activations