© 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. 23-RESID-POST-AA
    6. 669
    Prev
    Next
    INDEX
    Explanations

    Ab

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    濒临
    -0.07
    userRepository
    -0.07
    )new
    -0.06
    上升
    -0.06
    onation
    -0.06
    永不
    -0.06
    ↵↵↵↵↵↵
    -0.06
     продолж
    -0.06
    _pushButton
    -0.06
    ?”
    -0.06
    POSITIVE LOGITS
    ifi
    0.08
     авто
    0.07
     entrega
    0.07
     Manager
    0.07
    بح
    0.07
    SO
    0.07
     centerpiece
    0.06
     Ratio
    0.06
    Y
    0.06
     أ
    0.06
    Activations Density 0.004%

    No Known Activations