© 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. 107914
    Prev
    Next
    INDEX
    Explanations

    Code/technical documentation

    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
    /stretch
    -0.33
    orage
    -0.31
     Infos
    -0.27
    ãĥ«ãĥī
    -0.26
    inia
    -0.26
    utivo
    -0.26
    ANTE
    -0.26
    isseur
    -0.26
    讣
    -0.25
    ASTE
    -0.25
    POSITIVE LOGITS
     now
    0.35
    .
    0.30
     Now
    0.30
    se
    0.29
     (
    0.29
    çİ°åľ¨çļĦ
    0.29
    0.27
     "
    0.27
    ,
    0.26
    ...
    0.26
    Activations Density 0.910%

    No Known Activations