© 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. 27-TRANSCODER-HP
    7. 58001
    Prev
    Next
    INDEX
    Explanations

    metadata

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ench
    -0.27
    ient
    -0.27
     urb
    -0.25
     pr
    -0.25
     coast
    -0.25
    Numer
    -0.24
    ä½Ļ人
    -0.24
    ortion
    -0.24
     (+
    -0.24
    egend
    -0.24
    POSITIVE LOGITS
    ä¿¡æģ¯åıijå¸ĥ
    0.33
    ä¿¡æģ¯
    0.32
    èħ¾
    0.29
    åŁºæľ¬ä¿¡æģ¯
    0.28
    _about
    0.27
    é³ı
    0.27
     information
    0.27
     informations
    0.26
    æĥħåł±ãĤĴ
    0.26
    转åŀĭåįĩ级
    0.25
    Activations Density 0.020%

    No Known Activations