© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40784
    Prev
    Next
    INDEX
    Explanations

    something

    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
    Negative Logits
    <|endoftext|>
    -0.30
     properties
    -0.30
     indicators
    -0.27
     markers
    -0.27
     colors
    -0.27
     materials
    -0.26
     trials
    -0.26
     areas
    -0.26
     containers
    -0.25
     proteins
    -0.25
    POSITIVE LOGITS
     gigantic
    0.38
    æѤç§į
    0.35
     shitty
    0.34
    æŃ¤é¡¹
    0.34
    åı¯æĢķçļĦ
    0.34
     insanely
    0.33
    *I
    0.33
     unbelievable
    0.33
    çĻ½çĻ½
    0.33
     pricey
    0.32
    Activations Density 17.084%

    No Known Activations