© 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. 35-TRANSCODER-HP
    7. 39517
    Prev
    Next
    INDEX
    Explanations

    Chinese characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æħĬ
    -0.26
    mark
    -0.25
    tics
    -0.25
    incipal
    -0.24
    urre
    -0.24
     terms
    -0.24
     tide
    -0.24
    Terms
    -0.24
    SACTION
    -0.24
    macros
    -0.24
    POSITIVE LOGITS
    ä¸įåı¯ä»¥
    0.32
    0.30
    ¥¿
    0.29
    ä¸įä½Ĩ
    0.28
    ä¸įä»ħè¦ģ
    0.27
    ä¸įåı¯èĥ½
    0.25
    ä¸Ģæīĭ
    0.24
     being
    0.24
    çĻ¾åĪĨä¹ĭ
    0.23
    éľĢè¦ģçĶ¨åĪ°
    0.23
    Activations Density 0.202%

    No Known Activations