INDEX

Explanations

conjunctions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æİ¨éĢģ

-0.26

role

-0.25

çı¥

-0.25

åīįåĲİ

-0.24

ivr

-0.24

åĪĨéħį

-0.24

dur

-0.24

ä¸įåıĺ

-0.23

 minions

-0.23

ANTE

-0.23

POSITIVE LOGITS

plementation

0.25

.sponge

0.24

åı¦ä¸Ģä½į

0.24

 NONINFRINGEMENT

0.24

inen

0.24

ilege

0.23

è®¸åı¯è¯ģ

0.23

 proceed

0.22

äºĶçĻ¾

0.22

çİ°

0.22

Activations Density 0.004%

conjunctions

No Comments

No Known Activations