© 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. 39368
    Prev
    Next
    INDEX
    Explanations

    hydro

    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
     accordingly
    -0.25
     '@/
    -0.25
     [('
    -0.24
     forwarded
    -0.24
     зÑĢ
    -0.24
    çĥŁçģ«
    -0.23
    æĺ¯ä¸Ģéĥ¨
    -0.23
     rigged
    -0.23
     forwarding
    -0.22
     pursuing
    -0.22
    POSITIVE LOGITS
    cia
    0.41
    can
    0.41
    cou
    0.40
    carbon
    0.39
    cy
    0.39
    cle
    0.39
    cn
    0.38
    cbc
    0.38
    gli
    0.38
    ci
    0.38
    Activations Density 11.044%

    No Known Activations