© 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. 29655
    Prev
    Next
    INDEX
    Explanations

    (

    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
     lol
    -0.08
    恢复正常
    -0.07
    _mappings
    -0.07
    إصابة
    -0.07
    젰
    -0.07
     medieval
    -0.06
    ∴
    -0.06
    經
    -0.06
    比如
    -0.06
    提高
    -0.06
    POSITIVE LOGITS
    vertical
    0.07
    皿
    0.07
    🕸
    0.06
    reuse
    0.06
    ريك
    0.06
     hikes
    0.06
    ifter
    0.06
     sharks
    0.06
    七星
    0.06
    conda
    0.06
    Activations Density 0.006%

    No Known Activations