© 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. 39542
    Prev
    Next
    INDEX
    Explanations

    ST

    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
     stand
    -0.33
     stood
    -0.32
     stands
    -0.31
     standing
    -0.31
    stands
    -0.31
    stand
    -0.30
    igor
    -0.30
     res
    -0.28
    im
    -0.28
    iqu
    -0.27
    POSITIVE LOGITS
    éĽĩ
    0.28
    çĭĦ
    0.27
    @Id
    0.27
    onaut
    0.26
    /DD
    0.26
     NYT
    0.26
    ST
    0.26
    ðĿijº
    0.25
     newState
    0.25
     Dee
    0.25
    Activations Density 0.815%

    No Known Activations