© 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 EvalsExportsinterp-engineNEWAPI 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. 7499
    Prev
    Next
    INDEX
    Explanations

    rates of change

    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
    𝘛
    -0.08
     reun
    -0.08
     Organization
    -0.07
    😃
    -0.07
     cbo
    -0.07
    Subsystem
    -0.07
    GroupBox
    -0.07
     mul
    -0.07
    栉
    -0.07
    殚
    -0.07
    POSITIVE LOGITS
    กฎหมาย
    0.07
     airflow
    0.07
    اش
    0.07
     factual
    0.07
    וקר
    0.07
    ="$
    0.07
    展出
    0.07
    Flutter
    0.06
    krit
    0.06
    educated
    0.06
    Activations Density 0.116%

    No Known Activations