INDEX

Explanations

Beginning of sentences

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç²¾

-0.32

 slice

-0.30

 share

-0.29

 sleep

-0.28

Terr

-0.27

BAR

-0.26

æĺ¯ä¸ª

-0.25

 section

-0.25

use

-0.24

 comp

-0.24

POSITIVE LOGITS

urement

0.27

 Lage

0.26

ponsible

0.25

ÑĭÐ²Ð°ÑİÑĤ

0.25

uras

0.25

 evacuate

0.25

urses

0.25

èĩ¾

0.24

æĹłåģ¿

0.24

hythm

0.24

Activations Density 0.002%

Beginning of sentences

No Comments

No Known Activations