© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26223
    Prev
    Next
    INDEX
    Explanations

    tinnitus

    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
     sweetheart
    -0.07
     matcher
    -0.07
     ngược
    -0.07
     strain
    -0.07
    ummies
    -0.06
    .sprite
    -0.06
    當時
    -0.06
    nt
    -0.06
    🅶
    -0.06
     concentrate
    -0.06
    POSITIVE LOGITS
    Two
    0.07
    ethoven
    0.07
    innitus
    0.07
    remember
    0.07
    事业发展
    0.07
    跂
    0.07
    要闻
    0.07
     Taipei
    0.07
    ложен
    0.07
    長い
    0.07
    Activations Density 0.002%

    No Known Activations