© 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. 25-TRANSCODER-HP
    7. 107314
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lesbische
    -0.21
    orative
    -0.21
     Erotische
    -0.21
    -door
    -0.21
    -town
    -0.21
    -stars
    -0.21
    -mounted
    -0.20
     salopes
    -0.20
    -wage
    -0.20
    -dollar
    -0.20
    POSITIVE LOGITS
     (
    0.28
    0.28
     R
    0.28
     g
    0.26
     de
    0.25
     C
    0.25
     An
    0.25
     Part
    0.24
     a
    0.24
     Pr
    0.24
    Activations Density 1.270%

    No Known Activations