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. 92197
    Prev
    Next
    INDEX
    Explanations

    Second-person possessive pronouns

    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
    transforms
    -0.07
    (tmp
    -0.06
    癗
    -0.06
    цен
    -0.06
    integral
    -0.06
    붑
    -0.06
     Kaepernick
    -0.06
    summ
    -0.06
    协调发展
    -0.06
    Fair
    -0.06
    POSITIVE LOGITS
    .emit
    0.07
     attravers
    0.07
    ,out
    0.07
     ly
    0.06
    카
    0.06
    嗖
    0.06
    %%↵
    0.06
     Ни
    0.06
     manually
    0.06
    省市
    0.06
    Activations Density 0.005%

    No Known Activations