INDEX

Explanations

Locations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Neh

-0.28

å°ıä¼Ļä¼´ä»¬

-0.27

 fund

-0.25

ekt

-0.25

fund

-0.25

okus

-0.25

éĿĴ

-0.24

job

-0.24

.vo

-0.24

RACT

-0.24

POSITIVE LOGITS

à¹Į

0.30

utters

0.28

emean

0.28

roller

0.28

æĳ©æīĺ

0.27

ÑģÑĤÐ¾Ð»ÑĮ

0.27

 Reco

0.27

ResultsController

0.27

alty

0.26

 determinant

0.26

Activations Density 0.007%

Locations

No Comments

No Known Activations