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. 15-RESID-POST-AA
    6. 111125
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    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
     supper
    -0.08
     Numeric
    -0.08
     crear
    -0.07
     נש
    -0.07
     havoc
    -0.07
     nug
    -0.07
     thác
    -0.07
     emploi
    -0.07
     delle
    -0.07
    ΐ
    -0.07
    POSITIVE LOGITS
    ControlItem
    0.08
     object
    0.08
    (Position
    0.08
     FRAME
    0.07
    name
    0.07
    _unit
    0.07
    Position
    0.07
     include
    0.07
    Target
    0.07
    FullName
    0.07
    Activations Density 0.001%

    No Known Activations