© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 149333
    Prev
    Next
    INDEX
    Explanations

    internal

    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
    Negative Logits
    å®ŀéĻħä¸Ĭ
    -0.27
     actually
    -0.27
     latest
    -0.25
    æŃ£åĢ¼
    -0.25
     covert
    -0.25
     appropri
    -0.24
     much
    -0.23
    ä¸į失
    -0.23
    å°ıå¿ĥ翼翼
    -0.23
     actual
    -0.23
    POSITIVE LOGITS
    edly
    0.36
    ingly
    0.30
    ically
    0.27
    lessly
    0.26
    isses
    0.26
    CX
    0.25
    istically
    0.25
    ISR
    0.25
    ably
    0.24
    pitch
    0.24
    Activations Density 1.308%

    No Known Activations