© 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. 39607
    Prev
    Next
    INDEX
    Explanations

    vacation trips

    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
     the
    -0.28
     move
    -0.28
     strike
    -0.27
     ride
    -0.27
     visit
    -0.27
     walk
    -0.27
     scan
    -0.26
     match
    -0.26
    jective
    -0.25
     deal
    -0.25
    POSITIVE LOGITS
     biscuits
    0.28
    åı£è¢ĭ
    0.28
     campground
    0.28
     roadside
    0.27
    çļĦè¡£æľį
    0.26
    饺åŃIJ
    0.26
    burger
    0.26
     balcony
    0.25
     balcon
    0.25
    éĺ³åı°
    0.25
    Activations Density 4.615%

    No Known Activations