© 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. 107989
    Prev
    Next
    INDEX
    Explanations

    and

    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
    -or
    -0.31
    çĶ°
    -0.28
     uncon
    -0.27
    .or
    -0.26
    çļĦæľīæķĪ
    -0.25
    enes
    -0.25
    lan
    -0.24
    â½¥
    -0.24
     OR
    -0.24
    :<
    -0.24
    POSITIVE LOGITS
     Facts
    0.28
    culator
    0.26
    åİŁæĿ¥
    0.26
    éĺ²æ²»
    0.26
    angelog
    0.26
    ellaneous
    0.25
    ilog
    0.24
     Hast
    0.23
    astically
    0.23
    oggle
    0.23
    Activations Density 0.934%

    No Known Activations