© 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. 12-TRANSCODER-HP
    7. 23809
    Prev
    Next
    INDEX
    Explanations

    experiments or responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oleon
    -0.32
    alem
    -0.28
    ceptive
    -0.27
    æĶ¯æĮģåĬĽåº¦
    -0.25
     overlays
    -0.25
    å§Ķç»Ħç»ĩ
    -0.25
    acr
    -0.24
    _singular
    -0.24
    èĵĵ
    -0.24
    (DBG
    -0.23
    POSITIVE LOGITS
    åĩºæīĭ
    0.29
    ISC
    0.27
     factor
    0.27
    æĭħè´Ł
    0.26
    é¬ĵ
    0.25
     stepping
    0.24
     Macy
    0.24
    iring
    0.24
     Grades
    0.23
    çĿĢ
    0.23
    Activations Density 0.003%

    No Known Activations