© 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. 107461
    Prev
    Next
    INDEX
    Explanations

    medical abstracts

    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
    ç²īæľ«
    -0.29
    夫
    -0.28
    ANTED
    -0.26
    åŁĭ
    -0.25
     Crown
    -0.25
    æİĤ
    -0.25
    gie
    -0.25
    å«ģ
    -0.24
    åıijéħµ
    -0.24
    ek
    -0.24
    POSITIVE LOGITS
     Gos
    0.28
    ÑĩаÑģ
    0.28
     offsetof
    0.28
     gymn
    0.27
    èĨĢ
    0.26
    æħĪæĤ²
    0.26
    åĨĻåŃĹ
    0.25
    ç¯ĵ
    0.25
    lö
    0.25
    taÅŁ
    0.25
    Activations Density 0.947%

    No Known Activations