© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 5676
    Prev
    Next
    INDEX
    Explanations

    numerical and location information

    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
     Thoughts
    -0.07
    三四
    -0.07
     disgusted
    -0.07
    提炼
    -0.07
     Jal
    -0.07
    很想
    -0.07
    낏
    -0.07
    目前已经
    -0.07
    体内
    -0.07
    胪
    -0.07
    POSITIVE LOGITS
    '];
↵
↵
    0.07
    _years
    0.07
     annotation
    0.07
     ww
    0.07
    redd
    0.07
     centre
    0.07
    linewidth
    0.07
     proclaimed
    0.07
    Hit
    0.07
    _role
    0.07
    Activations Density 0.266%

    No Known Activations