INDEX

Explanations

Occupations/roles

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 burial

-0.25

æł¹æľ¬

-0.25

resh

-0.24

åľ°è¯´

-0.24

å¿Į

-0.24

 lesions

-0.23

å£®

-0.23

(bits

-0.23

è·Łå¥¹

-0.23

å©¦

-0.23

POSITIVE LOGITS

ena

0.27

 circum

0.27

 skim

0.25

åľĪåŃĲ

0.25

oeff

0.24

ansk

0.24

 taste

0.24

æľĢåĲİä¸Ģæ¬¡

0.24

ICS

0.24

oad

0.24

Activations Density 11.350%

Occupations/roles

No Comments

No Known Activations