© 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. 109075
    Prev
    Next
    INDEX
    Explanations

    bad smells

    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
    uchar
    -0.27
    积æŀģéħįåIJĪ
    -0.27
    被åĬ¨
    -0.27
    æŬ
    -0.25
     AAC
    -0.25
     matched
    -0.25
     dem
    -0.24
    两åı¥
    -0.24
    ä¸İä¸ŃåĽ½
    -0.24
     matcher
    -0.24
    POSITIVE LOGITS
    åĿij
    0.30
    èĩŃ
    0.28
    поÑĩ
    0.27
    çİij
    0.26
    iji
    0.25
    (od
    0.25
    ieve
    0.24
     chẳng
    0.24
    çĶŁç´ł
    0.24
    ski
    0.24
    Activations Density 0.927%

    No Known Activations