© 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. 62134
    Prev
    Next
    INDEX
    Explanations

    masked

    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
    enic
    -0.08
    周期
    -0.07
     desert
    -0.07
     spac
    -0.07
     Dy
    -0.07
    etheus
    -0.06
    ồi
    -0.06
    ፡
    -0.06
    攮
    -0.06
    鲕
    -0.06
    POSITIVE LOGITS
     mAdapter
    0.07
    شعار
    0.07
    ��
    0.07
     широко
    0.07
    صدق
    0.07
    告诉我
    0.07
     משתמש
    0.06
     Beacon
    0.06
    很长
    0.06
    /********
    0.06
    Activations Density 0.003%

    No Known Activations