© 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. 12-TRANSCODER-HP
    7. 23415
    Prev
    Next
    INDEX
    Explanations

    Machine generated text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeneratedValue
    -0.29
     Indo
    -0.25
    楹
    -0.25
    ingo
    -0.25
    æĮĪ
    -0.24
    姥
    -0.23
    çĥŃéĶĢ
    -0.23
     Dissertation
    -0.23
    Whole
    -0.23
     Definitions
    -0.23
    POSITIVE LOGITS
    羣æŃ£çļĦ
    0.28
    ä½ıåľ¨
    0.28
    羣æŃ£
    0.26
    ograf
    0.26
    utz
    0.26
    åĽ½å®¶å®īåħ¨
    0.25
    Witness
    0.24
    -eye
    0.24
    çĿ
    0.24
    za
    0.24
    Activations Density 0.001%

    No Known Activations