© 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. 129850
    Prev
    Next
    INDEX
    Explanations

    say "bag" words

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    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
    𝐽
    -0.07
     nav
    -0.07
    clip
    -0.07
     [].
    -0.07
    ัย
    -0.07
    Cancellation
    -0.07
    ⴹ
    -0.06
    图片来源
    -0.06
     depot
    -0.06
     entitlement
    -0.06
    POSITIVE LOGITS
     oder
    0.07
    orphic
    0.07
     الرحمن
    0.07
    uminum
    0.07
     Entire
    0.07
    ilage
    0.06
    oleon
    0.06
    isco
    0.06
    	string
    0.06
     Beispiel
    0.06
    Activations Density 0.089%

    No Known Activations