© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 23224
    Prev
    Next
    INDEX
    Explanations

    sexual content and positive feelings

    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
    fell
    -0.08
    Sac
    -0.07
     Window
    -0.07
    =yes
    -0.07
    صبح
    -0.07
    ȑ
    -0.07
     bụng
    -0.06
    Missing
    -0.06
    ⌒
    -0.06
     Sweat
    -0.06
    POSITIVE LOGITS
     прогноз
    0.07
     trailer
    0.07
     judge
    0.07
    nP
    0.07
     Respect
    0.07
    爸爸
    0.07
     posts
    0.07
    +len
    0.07
     seats
    0.07
    *M
    0.06
    Activations Density 0.015%

    No Known Activations