© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5347
    Prev
    Next
    INDEX
    Explanations

    gon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }*/↵↵
    -0.28
    aturing
    -0.28
    anmar
    -0.27
    ammer
    -0.26
     -->č↵č↵
    -0.26
     derivatives
    -0.26
    -on
    -0.26
    çIJħ
    -0.25
    anning
    -0.25
    —an
    -0.25
    POSITIVE LOGITS
    çļĦå½±åĵį
    0.31
    .FC
    0.24
    èĢĮåĩº
    0.24
    æĸ¯å¡Ķ
    0.24
    大éĻĨ
    0.24
    æµĬ
    0.24
    讶
    0.24
    mandatory
    0.24
    @student
    0.23
     simult
    0.23
    Activations Density 0.133%

    No Known Activations