© 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. 24220
    Prev
    Next
    INDEX
    Explanations

    published

    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
    ingly
    -0.29
    çļĦçŃĶæ¡Ī
    -0.26
     PIC
    -0.26
    æ¯ı个人çļĦ
    -0.26
    ings
    -0.25
     mạch
    -0.25
    çļĦéĤ£ä¸Ģ
    -0.25
    INGS
    -0.24
    æijĨåľ¨
    -0.24
    fully
    -0.24
    POSITIVE LOGITS
     elsewhere
    0.28
    isl
    0.25
     late
    0.25
    orte
    0.25
    æ¶ķ
    0.25
     pam
    0.24
    çĪ¶æ¯į
    0.24
    çľ¼åħī
    0.24
    èĢģçĪ¸
    0.24
    getParent
    0.24
    Activations Density 0.034%

    No Known Activations