© 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. 23-RESID-POST-AA
    11. 507
    Prev
    Next
    INDEX
    Explanations

    math problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stamped
    -0.07
     perfection
    -0.07
    完美的
    -0.07
     cultured
    -0.06
    钰
    -0.06
     likewise
    -0.06
    읊
    -0.06
    栐
    -0.06
    ystal
    -0.06
    죳
    -0.06
    POSITIVE LOGITS
     horizontally
    0.08
     extents
    0.07
    #\
    0.07
    _horizontal
    0.07
    ’av
    0.07
     ?>↵↵↵
    0.07
     تحت
    0.07
    Md
    0.07
    amide
    0.07
    	md
    0.07
    Activations Density 0.031%

    No Known Activations