© 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. 5745
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĥ¯
    -0.26
    ç¼Ń
    -0.25
    ilarity
    -0.25
    xFB
    -0.25
    èĢģé¾ĦåĮĸ
    -0.24
     clubs
    -0.24
    娶
    -0.24
    getC
    -0.23
    %</
    -0.23
    cripcion
    -0.23
    POSITIVE LOGITS
    ä¾ĭè¡Į
    0.27
    æĬĬæīĭ
    0.26
    æī¹éĩı
    0.26
    ÑģÑĤавка
    0.25
    è·³è·ĥ
    0.25
    çļ²
    0.24
    mine
    0.24
    æŀľæĸŃ
    0.24
    èįīåľ°
    0.23
    人æĸĩ
    0.23
    Activations Density 0.794%

    No Known Activations

    This feature has no known activations.