© 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. 107522
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ynamics
    -0.26
    anny
    -0.26
    ialect
    -0.25
     миÑĢа
    -0.24
    ása
    -0.24
     Może
    -0.24
    _engine
    -0.24
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    -0.24
     massac
    -0.24
    _sup
    -0.24
    POSITIVE LOGITS
    æ¯ıä¸Ģ
    0.32
    该
    0.31
     each
    0.29
    Each
    0.29
    å¢Ļä¸Ĭ
    0.28
    沿éĢĶ
    0.28
     holes
    0.28
     counter
    0.27
     plates
    0.27
    æ¯ı次
    0.27
    Activations Density 0.951%

    No Known Activations