© 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. 27-TRANSCODER-HP
    7. 8206
    Prev
    Next
    INDEX
    Explanations

    Mixed or generic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĤ¨çļĦåŃ©åŃIJ
    -0.27
    tram
    -0.26
    禽
    -0.25
    GRAM
    -0.24
     fucks
    -0.24
     contiguous
    -0.24
    plr
    -0.24
    (vehicle
    -0.24
     Musk
    -0.24
     EVE
    -0.24
    POSITIVE LOGITS
    гоÑĢ
    0.26
    nelly
    0.25
    âķĹ
    0.24
    @endsection
    0.24
    emiah
    0.23
     pratic
    0.23
    ahoma
    0.23
    uh
    0.23
    ฯ
    0.23
    ments
    0.23
    Activations Density 0.001%

    No Known Activations