© 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
    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. 77409
    Prev
    Next
    INDEX
    Explanations

    references to assistant-level occupational titles and roles, especially in professional or academic contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    plx
    -0.07
    mv
    -0.07
    (spell
    -0.07
    [b
    -0.07
     böl
    -0.06
    <Member
    -0.06
    род
    -0.06
    [A
    -0.06
    	df
    -0.06
    (Entity
    -0.06
    POSITIVE LOGITS
    笠
    0.08
     hast
    0.07
    حوال
    0.07
    ят
    0.07
     assistant
    0.07
    INS
    0.07
    يرا
    0.07
    海峡
    0.07
     Howell
    0.07
    Attrib
    0.07
    Activations Density 0.018%

    No Known Activations