© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 1001
    Prev
    Next
    INDEX
    Explanations

    say "this"

    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
     현실
    -0.07
     stabbed
    -0.07
    Scan
    -0.07
    我没
    -0.06
     branded
    -0.06
    _Texture
    -0.06
    高山
    -0.06
    咦
    -0.06
    _VERBOSE
    -0.06
    平面
    -0.06
    POSITIVE LOGITS
     Deborah
    0.07
    פתיחת
    0.07
     вид
    0.07
     política
    0.07
     geht
    0.07
     inhib
    0.07
     شأن
    0.07
    执导
    0.07
     unacceptable
    0.06
    areas
    0.06
    Activations Density 0.140%

    No Known Activations