© 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. 107637
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     CWE
    -0.26
    çī¹
    -0.25
     typically
    -0.24
    讯
    -0.24
     either
    -0.24
    iness
    -0.24
    è¦ģä¹Ī
    -0.24
    åĥļ
    -0.24
    ReturnValue
    -0.24
     withdraw
    -0.24
    POSITIVE LOGITS
     tightening
    0.29
     abused
    0.28
    éĿŀ常好
    0.28
     spice
    0.27
     tightened
    0.27
    å¾Ī好
    0.26
    åĩłå®¶
    0.26
    oji
    0.25
    便æĺ¯
    0.25
    æĬ¥ç¤¾
    0.25
    Activations Density 0.978%

    No Known Activations