Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 19-RESID-POST-AA
    6. 71823
    Prev
    Next
    INDEX
    Explanations

    -get

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     depot
    -0.07
     الجمعة
    -0.07
     claimed
    -0.07
    에도
    -0.06
     Utt
    -0.06
     euros
    -0.06
    Typed
    -0.06
    eyJ
    -0.06
    莜
    -0.06
    żeli
    -0.06
    POSITIVE LOGITS
     lique
    0.08
     (!_
    0.07
    DCALL
    0.07
    �
    0.07
    NOT
    0.06
    mith
    0.06
    (language
    0.06
     kinase
    0.06
    olute
    0.06
     lin
    0.06
    Activations Density 0.002%

    No Known Activations