© 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. 107396
    Prev
    Next
    INDEX
    Explanations

    technical and scientific writing

    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
    åħ«å¹´
    -0.29
     prere
    -0.25
     boot
    -0.25
    agrid
    -0.24
    l
    -0.23
     culturally
    -0.23
    _REGION
    -0.23
     frankfurt
    -0.23
    .ca
    -0.23
     Region
    -0.23
    POSITIVE LOGITS
    å¾ĹçĽĬäºİ
    0.28
    羣æŃ£åģļåĪ°
    0.26
     tongue
    0.25
    çĴº
    0.25
    å½ĵä¹ĭ
    0.25
    羣çļĦå¾Ī
    0.24
    —the
    0.23
    çĶ±äºİ
    0.23
    æģ¯
    0.23
    ife
    0.23
    Activations Density 0.130%

    No Known Activations