© 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. 108357
    Prev
    Next
    INDEX
    Explanations

    standard amounts

    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
    otherwise
    -0.29
     otherwise
    -0.29
    ilities
    -0.27
    ibili
    -0.27
    ippi
    -0.26
     judges
    -0.26
    еÑĩно
    -0.25
    cio
    -0.24
    egin
    -0.24
    æĪ¿å±ĭ
    -0.24
    POSITIVE LOGITS
     amt
    0.30
     diameter
    0.28
     equivalent
    0.28
     deadline
    0.27
     total
    0.27
    itude
    0.27
     approximate
    0.27
     length
    0.26
     width
    0.26
     wavelength
    0.26
    Activations Density 0.934%

    No Known Activations