© 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. 11-RESID-POST-AA
    11. 1535
    Prev
    Next
    INDEX
    Explanations

    selecting/choosing

    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
    举起
    -0.07
    _FieldOffsetTable
    -0.07
    (Vector
    -0.07
     funk
    -0.06
     Conflict
    -0.06
    心境
    -0.06
     CSA
    -0.06
     força
    -0.06
    炖
    -0.06
    *z
    -0.06
    POSITIVE LOGITS
     helper
    0.08
     abundant
    0.07
     chips
    0.07
     directly
    0.07
    (reader
    0.07
     LABEL
    0.07
    chemical
    0.07
    agram
    0.07
    Definition
    0.07
    _manager
    0.06
    Activations Density 0.043%

    No Known Activations