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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 92182
    Prev
    Next
    INDEX
    Explanations

    global statistics and data

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _atual
    -0.07
    -focus
    -0.07
     calmly
    -0.07
    _outer
    -0.07
    �
    -0.07
    _successful
    -0.07
    돕
    -0.07
    izione
    -0.06
     FixedUpdate
    -0.06
    严禁
    -0.06
    POSITIVE LOGITS
    EIF
    0.08
     alarmed
    0.08
    Hair
    0.07
     blob
    0.07
    şa
    0.07
     Ngb
    0.07
    蚁
    0.07
    Means
    0.07
     noted
    0.07
    بك
    0.07
    Activations Density 0.020%

    No Known Activations