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. 1681
    Prev
    Next
    INDEX
    Explanations

    cruise

    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
    (TYPE
    -0.08
    _REPLACE
    -0.08
    ዘ
    -0.07
    了一口
    -0.07
    (zone
    -0.07
    Partition
    -0.07
     deriv
    -0.07
    anneer
    -0.07
    考え
    -0.07
    뛔
    -0.07
    POSITIVE LOGITS
    决心
    0.08
     Gill
    0.07
     Dub
    0.07
    -loaded
    0.06
    .ScrollBars
    0.06
     whales
    0.06
    _markers
    0.06
     ischem
    0.06
     AND
    0.06
    쯘
    0.06
    Activations Density 0.005%

    No Known Activations