© 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. 92714
    Prev
    Next
    INDEX
    Explanations

    mixing

    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
    相遇
    -0.07
    ⇣
    -0.07
    }else
    -0.07
    と思
    -0.07
     (↵
    -0.06
     =================================================================================
    -0.06
    ane
    -0.06
    MASConstraintMaker
    -0.06
     hour
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     jig
    0.07
    理智
    0.07
    移民
    0.07
    _partitions
    0.07
    retrieve
    0.07
     hardships
    0.07
     Pol
    0.07
     Silicon
    0.07
    пы
    0.07
     aute
    0.07
    Activations Density 0.002%

    No Known Activations