INDEX

Explanations

7

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

äººå·¥

-0.28

 conc

-0.27

áº¤

-0.25

 themselves

-0.25

 Stam

-0.25

ITE

-0.25

ucci

-0.25

gles

-0.24

letic

-0.24

acer

-0.24

POSITIVE LOGITS

SetActive

0.27

ponsored

0.25

 nargin

0.24

oxide

0.24

hydrate

0.24

æĸ¹éĿ¢çļĦ

0.24

 households

0.24

æĪĲè¯Ń

0.24

maids

0.24

 ÑģÐ»ÑĥÑĩÐ°Ñı

0.23

Activations Density 0.001%

7

No Comments

No Known Activations