© 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. 15-RESID-POST-AA
    11. 48923
    Prev
    Next
    INDEX
    Explanations

    side

    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
    lett
    -0.07
    ན
    -0.07
    jh
    -0.07
    邗
    -0.06
    下乡
    -0.06
    .FieldName
    -0.06
    stęp
    -0.06
    ⵣ
    -0.06
    иш
    -0.06
    nev
    -0.06
    POSITIVE LOGITS
    weeks
    0.08
     prospect
    0.07
    Shortly
    0.07
    煌
    0.07
    ();
↵
↵
↵
    0.07
     security
    0.07
     Foot
    0.07
     Soap
    0.06
    exceptions
    0.06
     comparator
    0.06
    Activations Density 0.025%

    No Known Activations