© 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. 40304
    Prev
    Next
    INDEX
    Explanations

    Standards and Methods

    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
     standards
    -0.63
     Standards
    -0.54
    è¶ħæłĩ
    -0.38
    æłĩåĩĨ
    -0.35
    Stand
    -0.34
     fucking
    -0.29
    è¾¾æłĩ
    -0.28
     ÑģÑĤанд
    -0.27
    stand
    -0.27
     hostages
    -0.27
    POSITIVE LOGITS
     EMS
    0.40
     CRS
    0.40
     MAS
    0.35
     SAS
    0.34
     CAS
    0.34
    IMA
    0.33
     PAS
    0.33
     PIN
    0.33
     EPS
    0.33
     POS
    0.32
    Activations Density 22.870%

    No Known Activations