© 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. 8798
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
     instruments
    -0.31
    ä¸ĢéŨ
    -0.31
    éĩįçĤ¹é¡¹çĽ®
    -0.30
    æĢ§çĸ¾çĹħ
    -0.30
     projects
    -0.30
     hormones
    -0.30
     functions
    -0.30
     drugs
    -0.29
    FUNCTION
    -0.28
     religions
    -0.28
    POSITIVE LOGITS
    DOCUMENT
    0.28
    redni
    0.28
    uel
    0.28
     Blanch
    0.27
    ĶåĽŀ
    0.26
    UCH
    0.25
    -worker
    0.25
    _PG
    0.25
    еÑĢиал
    0.25
    worker
    0.24
    Activations Density 0.000%

    No Known Activations