Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 69083
    Prev
    Next
    INDEX
    Explanations

    Browser computer cookies

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     concerned
    -0.07
    根本
    -0.07
     unleashed
    -0.07
    兴致
    -0.06
    NEG
    -0.06
    LB
    -0.06
     rightful
    -0.06
    צדק
    -0.06
     polishing
    -0.06
     בחיים
    -0.06
    POSITIVE LOGITS
    ница
    0.07
    」
    0.07
    .oracle
    0.07
    -input
    0.07
    Bl
    0.07
    -sign
    0.07
    _MALLOC
    0.06
    
    0.06
     mamma
    0.06
    .encrypt
    0.06
    Activations Density 0.001%

    No Known Activations