© 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. 57125
    Prev
    Next
    INDEX
    Explanations

    the

    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
    eci
    -0.30
    oste
    -0.27
    ETS
    -0.26
    æĹłç¼ĺ
    -0.25
     Drops
    -0.25
    oco
    -0.25
    åķĨæĬ¥
    -0.25
    contr
    -0.24
    ëŀ©
    -0.24
    ubre
    -0.24
    POSITIVE LOGITS
     mole
    0.28
    æ»ij
    0.27
     crowned
    0.24
    饶
    0.24
    _wf
    0.23
    çİ©æ³ķ
    0.23
    婺
    0.23
    éĻŁ
    0.22
    erk
    0.22
    samp
    0.22
    Activations Density 0.008%

    No Known Activations