INDEX

Explanations

logical consequence indicators

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ableView

-0.28

 Placeholder

-0.26

chy

-0.25

æ¯Ķäºļ

-0.24

.RunWith

-0.24

æĥ³è±¡åĬĽ

-0.24

illet

-0.24

Utt

-0.24

oger

-0.24

 Ð¿Ð»

-0.23

POSITIVE LOGITS

prs

0.29

 Useful

0.28

ä¿±

0.27

 useful

0.27

å¸¸çĶ¨

0.27

å¸¸å¸¸

0.26

util

0.26

dps

0.26

çİ°ä»£åĮĸ

0.25

ãĤĴéģ¸

0.25

Activations Density 0.008%

logical consequence indicators

No Comments

No Known Activations