© 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. 7-RESID-POST-AA
    11. 8560
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vĩnh
    -0.07
     jóvenes
    -0.07
     camar
    -0.07
     Adolescent
    -0.07
    Ѳ
    -0.07
    แปลก
    -0.07
    的年轻人
    -0.07
     occult
    -0.07
    ymbol
    -0.07
     Españ
    -0.07
    POSITIVE LOGITS
     ['
    0.08
     review
    0.07
    审议通过
    0.07
    确诊病例
    0.07
    אן
    0.06
    贝
    0.06
    !("
    0.06
     "','
    0.06
     PubMed
    0.06
    בטיח
    0.06
    Activations Density 0.021%

    No Known Activations