© 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. 23-TRANSCODER-HP
    7. 23810
    Prev
    Next
    INDEX
    Explanations

    technical, mixed contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vs
    -0.28
    åIJĴ
    -0.28
    纵åIJij
    -0.26
    mu
    -0.25
    æľĢä¼ĺ
    -0.25
    åĪĽéĢłæĢ§
    -0.25
    碳éħ¸
    -0.25
    .StoredProcedure
    -0.25
    Industrial
    -0.25
    оÑģÑĤей
    -0.25
    POSITIVE LOGITS
    è§ĦåĪĻ
    0.29
    ä½ĵåĪ¶
    0.29
    ä»·ä½į
    0.29
    åĬŁ
    0.28
    ç»ĵå±Ģ
    0.27
    åĬĽåº¦
    0.27
    缮çļĦ
    0.27
    è§Ħ模
    0.27
    æĶ¶èİ·
    0.26
    magnitude
    0.26
    Activations Density 0.012%

    No Known Activations