© 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. 26297
    Prev
    Next
    INDEX
    Explanations

    ат

    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
    뤠
    -0.08
    忪
    -0.07
    떠
    -0.07
     adoles
    -0.07
    .logical
    -0.07
     vX
    -0.07
    🌜
    -0.07
    _IS
    -0.07
     ReactDOM
    -0.07
    (token
    -0.07
    POSITIVE LOGITS
     bert
    0.07
    borough
    0.07
    Evaluation
    0.06
    _hits
    0.06
    	th
    0.06
     opponents
    0.06
    XXXXXXXX
    0.06
     Belmont
    0.06
     Joan
    0.06
     downs
    0.06
    Activations Density 0.006%

    No Known Activations