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

    Neuronpedia

    APICircuit 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. 27-RESID-POST-AA
    6. 131045
    Prev
    Next
    INDEX
    Explanations

    punctuations

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    major
    -0.07
     Odds
    -0.07
     scr
    -0.07
    藝
    -0.07
    Leading
    -0.07
    reau
    -0.07
    va
    -0.07
    hab
    -0.07
    -role
    -0.06
    fin
    -0.06
    POSITIVE LOGITS
    ᶤ
    0.08
    .BigInteger
    0.07
    榃
    0.07
    ormap
    0.07
    .Debugf
    0.07
    戽
    0.07
     defensively
    0.07
    砹
    0.07
     kostenlose
    0.07
    omitempty
    0.06
    Activations Density 0.115%

    No Known Activations