INDEX

Explanations

Beginning of paragraphs

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

 Dodge

-0.31

routeParams

-0.28

gings

-0.27

æ²±

-0.27

æľīå¾Īå¤ļç§į

-0.26

æ¢¢

-0.25

 stretching

-0.25

bos

-0.25

 Fall

-0.25

amble

-0.24

POSITIVE LOGITS

OID

0.26

 gegenÃ¼ber

0.25

åİļåº¦

0.25

 Connected

0.25

åĸĪ

0.25

èŁ¹

0.25

æ²¼

0.24

REET

0.24

Jah

0.24

rey

0.24

Activations Density 0.002%

Beginning of paragraphs

No Comments

No Known Activations