© 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. 110274
    Prev
    Next
    INDEX
    Explanations

    research papers

    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
     diabetes
    -0.08
     hypertension
    -0.07
    장애인
    -0.07
    angan
    -0.07
     électrique
    -0.07
    aan
    -0.07
     società
    -0.07
    .dashboard
    -0.07
    caling
    -0.07
    تقليد
    -0.07
    POSITIVE LOGITS
    .opend
    0.07
     carriers
    0.07
     """↵
    0.07
     reb
    0.07
     recom
    0.07
    ured
    0.07
    输出
    0.07
    _Bl
    0.07
    vider
    0.06
     rotation
    0.06
    Activations Density 0.239%

    No Known Activations