© 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. 39988
    Prev
    Next
    INDEX
    Explanations

    references to sources

    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
    -security
    -0.28
    ValidationError
    -0.28
    buah
    -0.26
    çĺª
    -0.26
    å´Ń
    -0.25
    	buffer
    -0.25
    err
    -0.25
     account
    -0.25
    cro
    -0.24
    å®Ŀè´µçļĦ
    -0.24
    POSITIVE LOGITS
     goalkeeper
    0.34
     ESV
    0.32
     MLA
    0.31
     marketer
    0.29
     CWE
    0.29
    å¦Ĥæŀľçݩ家
    0.28
     guitarist
    0.27
    âĹĦ
    0.26
     Paypal
    0.26
    GPL
    0.26
    Activations Density 1.321%

    No Known Activations