© 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. 109205
    Prev
    Next
    INDEX
    Explanations

    structured text

    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
    ographics
    -0.26
     exp
    -0.26
    ç½´
    -0.26
     docs
    -0.25
     Tues
    -0.25
    åıªè¦ģä½ł
    -0.24
    ientes
    -0.24
    ogi
    -0.24
     cams
    -0.24
    æ²®
    -0.24
    POSITIVE LOGITS
     flipping
    0.28
    Park
    0.27
    SCP
    0.26
    (fl
    0.26
    اد
    0.25
    éĽªèĬ±
    0.24
    adro
    0.24
     flap
    0.24
    irim
    0.24
     helf
    0.24
    Activations Density 0.018%

    No Known Activations