© 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. 25-TRANSCODER-HP
    7. 107283
    Prev
    Next
    INDEX
    Explanations

    size and shape

    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
    매
    -0.27
    å·¥æľŁ
    -0.25
    è°ģ
    -0.25
    èį¡
    -0.25
    åİŁä»¶
    -0.24
     Cruc
    -0.24
    轶
    -0.24
     ########################################################################
    -0.24
    带走
    -0.24
    Construct
    -0.24
    POSITIVE LOGITS
    graded
    0.28
    çŃī级
    0.27
    稼
    0.25
     pob
    0.24
    cached
    0.24
    澡
    0.24
     stabilize
    0.24
    ãĥĿãĥ³
    0.24
     fuzz
    0.23
    D
    0.23
    Activations Density 1.445%

    No Known Activations