© 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. 107842
    Prev
    Next
    INDEX
    Explanations

    beauty and perfection

    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
    arking
    -0.26
    allon
    -0.26
    Borders
    -0.25
    -0.25
    ä¸¤åľ°
    -0.25
    _sequences
    -0.25
     stereotype
    -0.25
    sequences
    -0.25
    tere
    -0.24
    ibal
    -0.24
    POSITIVE LOGITS
    æ°Ķè´¨
    0.41
    qual
    0.38
    ç´łè´¨
    0.36
     radi
    0.34
    åĵģè´¨
    0.34
    é£İéĩĩ
    0.32
    è´¨
    0.32
     qual
    0.32
    radi
    0.32
    åĨħåľ¨
    0.31
    Activations Density 0.966%

    No Known Activations