INDEX

Explanations

with

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĿĲ

-0.29

éĤĦè¦ģ

-0.25

yst

-0.24

ampus

-0.24

 Materials

-0.24

 affected

-0.24

_over

-0.24

æ¶īæ¡Ī

-0.23

ek

-0.23

è¿ĺè¦ģ

-0.23

POSITIVE LOGITS

å²Ķ

0.28

 hypo

0.28

odge

0.26

OPTIONS

0.25

ä¼İ

0.25

 hypnot

0.25

urge

0.25

mf

0.24

perial

0.24

pants

0.23

Activations Density 0.003%

with

No Comments

No Known Activations