Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 120902
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atitude
    -0.07
     evidence
    -0.07
    бу
    -0.07
     debugging
    -0.07
    annel
    -0.07
    來
    -0.07
     grenades
    -0.07
    \Route
    -0.07
    _slope
    -0.07
     precautions
    -0.07
    POSITIVE LOGITS
     كسارة
    0.08
    California
    0.07
    شعور
    0.07
     yaklaşık
    0.07
     الأمريك
    0.07
     의사
    0.07
     רשימת
    0.07
     американ
    0.06
    PARATOR
    0.06
     paul
    0.06
    Activations Density 0.066%

    No Known Activations