© 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. 107183
    Prev
    Next
    INDEX
    Explanations

    lation

    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
    Negative Logits
     fog
    -0.33
    unny
    -0.26
    Iss
    -0.24
     forth
    -0.24
     race
    -0.24
    CID
    -0.24
    IVER
    -0.24
    erras
    -0.24
    float
    -0.23
    á»ĭch
    -0.23
    POSITIVE LOGITS
    reon
    0.30
     DISP
    0.29
     amph
    0.29
    绾
    0.28
    çļĦç¨ĭ度
    0.27
    interop
    0.27
    å½¢æĪIJçļĦ
    0.27
     disap
    0.27
     interrogation
    0.26
     interrog
    0.25
    Activations Density 0.976%

    No Known Activations