INDEX

Explanations

Past-tense verbs

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rig

-0.26

(!_

-0.24

togroup

-0.24

(;

-0.24

logue

-0.24

=!

-0.23

è¿ĻåĲį

-0.23

ritos

-0.23

 practitioner

-0.23

åģļå¤§åģļå¼º

-0.23

POSITIVE LOGITS

åĢ¼å¾Ĺ

0.27

anted

0.25

ast

0.25

å³°

0.25

weep

0.25

æĮĸ

0.25

 domina

0.25

 coeff

0.25

mins

0.24

peg

0.24

Activations Density 0.166%

Past-tense verbs

No Comments

No Known Activations