© 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. 108705
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     competition
    -0.27
    zes
    -0.26
    è°¤
    -0.26
    èµİ
    -0.25
    ä¹Łè®¸
    -0.25
    QRS
    -0.25
    èĤ®
    -0.25
    æ¯ĶèµĽ
    -0.24
    reas
    -0.24
    æĶ¹éĿ©
    -0.24
    POSITIVE LOGITS
    梯éĺŁ
    0.27
     _:
    0.25
    Interval
    0.24
    zik
    0.24
    ç¬Ķè®°æľ¬
    0.24
    weg
    0.23
    'l
    0.23
    å¿«æĬ¥
    0.23
     tóc
    0.23
     else
    0.23
    Activations Density 0.445%

    No Known Activations

    This feature has no known activations.