INDEX

Explanations

First-person pronouns

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

ç¬Ķ

-0.29

enti

-0.27

por

-0.26

 Booth

-0.26

ure

-0.25

 ç¬

-0.25

çŃĨ

-0.25

nant

-0.24

ese

-0.24

ful

-0.24

POSITIVE LOGITS

åģļçļĦäºĭ

0.30

 instead

0.28

INO

0.28

 dolphin

0.27

ä¹ĭä¸Ĭ

0.26

cba

0.26

 elsewhere

0.26

æĺ¯æĪĳçļĦ

0.25

instead

0.25

åģļçļĦäºĭæĥħ

0.25

Activations Density 0.024%

First-person pronouns

No Comments

No Known Activations