Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 92205
    Prev
    Next
    INDEX
    Explanations

    stochastic diffusion equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    手册
    -0.07
    ;">
    -0.06
     Liberals
    -0.06
    .con
    -0.06
    זרים
    -0.06
     skips
    -0.06
     miesięcy
    -0.06
    ็ก
    -0.06
     honest
    -0.06
    gün
    -0.06
    POSITIVE LOGITS
     Offline
    0.07
    Net
    0.07
     Collider
    0.07
     setLoading
    0.07
    Income
    0.07
     vivo
    0.07
    (↵
    0.07
     Cos
    0.07
     que
    0.07
     seine
    0.07
    Activations Density 0.009%

    No Known Activations