© 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. 108015
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    è¿Ļå¼ł
    -0.30
    FW
    -0.28
    å¹²æ¶ī
    -0.26
    æµģåĬ¨æĢ§
    -0.25
    CP
    -0.25
    è¯ĺ
    -0.25
    ä¸īä½įä¸Ģä½ĵ
    -0.25
    两åıª
    -0.24
    åģĮ
    -0.24
    åıijæĺİä¸ĵåĪ©
    -0.24
    POSITIVE LOGITS
    ilan
    0.27
    stringValue
    0.25
    она
    0.25
    客æĪ·æıIJä¾Ľ
    0.24
    å½ĵäºĭ
    0.24
    isNull
    0.24
    :".
    0.24
    !.↵↵
    0.24
    éĨ
    0.23
    _Parameter
    0.23
    Activations Density 0.002%

    No Known Activations