© 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. 107941
    Prev
    Next
    INDEX
    Explanations

    guilt

    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
    uste
    -0.27
    便
    -0.27
     comb
    -0.26
    atto
    -0.25
    abbo
    -0.25
    idas
    -0.25
     translated
    -0.25
     Tracks
    -0.24
     Abel
    -0.24
    romium
    -0.24
    POSITIVE LOGITS
    æľĪç»ı
    0.30
    -weight
    0.28
    çļĦå¿ĥ
    0.27
    å¿ĥè·³
    0.27
    ä¸įå®ī
    0.27
    scape
    0.26
    ^^^^
    0.26
     ör
    0.25
    oil
    0.25
     ngược
    0.25
    Activations Density 0.950%

    No Known Activations