© 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. 40090
    Prev
    Next
    INDEX
    Explanations

    R

    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
    è¶ĬãģĹ
    -0.28
    adiator
    -0.28
    rections
    -0.27
    istration
    -0.27
    ä¸įåħį
    -0.25
    -setup
    -0.24
    lée
    -0.24
    jong
    -0.24
    æİ¥åľ°æ°Ķ
    -0.23
    -ground
    -0.23
    POSITIVE LOGITS
     antis
    0.27
     absl
    0.27
     autob
    0.26
    çŃĸ
    0.25
    antis
    0.25
    ssa
    0.24
    å¤Ń
    0.24
    ettes
    0.24
     NSObject
    0.24
    AB
    0.24
    Activations Density 0.026%

    No Known Activations