© 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. 108062
    Prev
    Next
    INDEX
    Explanations

    diet

    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
    æĶ¶éĽĨ
    -0.28
    erner
    -0.26
    æ¶Ĥ
    -0.25
    æ¸ļ
    -0.25
    æ®ĸæ°ij
    -0.24
    èĿ¼
    -0.24
    åŁºåľ°
    -0.24
    =edge
    -0.24
    èļĤèļģ
    -0.23
    峡
    -0.23
    POSITIVE LOGITS
    æŀģ大
    0.25
    ropy
    0.24
    .localization
    0.24
    orch
    0.24
    ARGS
    0.24
    Ĩµ
    0.23
    ulled
    0.23
    Much
    0.23
    _SCHED
    0.23
    .CG
    0.23
    Activations Density 1.056%

    No Known Activations