© 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. 41675
    Prev
    Next
    INDEX
    Explanations

    what

    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
     conceive
    -0.07
    ]],
    -0.07
    🚹
    -0.07
    �
    -0.07
    Wrong
    -0.07
    цикл
    -0.06
    ᗢ
    -0.06
    比赛中
    -0.06
     conjunto
    -0.06
    Types
    -0.06
    POSITIVE LOGITS
    某某
    0.08
     الأم
    0.07
     iParam
    0.07
    硫
    0.07
    栎
    0.06
    洮
    0.06
    王爷
    0.06
    广州
    0.06
     parametro
    0.06
     WG
    0.06
    Activations Density 0.015%

    No Known Activations