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

    Neuronpedia

    Jacobian LensNEW
    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. 19-RESID-POST-AA
    11. 70546
    Prev
    Next
    INDEX
    Explanations

    say "LICENSE"

    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
    🧜
    -0.08
    硖
    -0.08
    麓
    -0.07
     später
    -0.07
    生活习惯
    -0.07
    咄
    -0.07
    碓
    -0.07
    ☽
    -0.07
    echa
    -0.07
    omidou
    -0.07
    POSITIVE LOGITS
    (B
    0.07
    Regions
    0.07
    _BREAK
    0.06
    =[],
    0.06
     MOV
    0.06
     samt
    0.06
     Kang
    0.06
    �
    0.06
    -position
    0.06
    roker
    0.06
    Activations Density 0.000%

    No Known Activations