© 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. 31-TRANSCODER-HP
    7. 18469
    Prev
    Next
    INDEX
    Explanations

    give

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»Ļ
    -0.90
    給
    -0.68
     give
    -0.66
     giving
    -0.65
     Give
    -0.64
     given
    -0.63
     Giving
    -0.62
    ç»ĻäºĨ
    -0.62
     gives
    -0.61
     gave
    -0.59
    POSITIVE LOGITS
     guidance
    0.27
    æī¾åĩĨ
    0.26
    äºĨ解ä¸Ģä¸ĭ
    0.26
    欢è¿İ大家
    0.25
     fragmentManager
    0.25
    housing
    0.25
     advice
    0.24
    ä¿¡æģ¯åıijå¸ĥ
    0.24
     them
    0.24
    locals
    0.24
    Activations Density 1.078%

    No Known Activations