INDEX

Explanations

Orthodontics and orthopedics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ERM

-0.28

enk

-0.27

èĬ¬

-0.27

ivid

-0.25

æĻĶ

-0.25

ellas

-0.25

 faithful

-0.25

jog

-0.24

_BIND

-0.24

ONGL

-0.24

POSITIVE LOGITS

iture

0.30

atal

0.29

ocial

0.27

ritten

0.26

ische

0.26

igital

0.26

ischen

0.26

icina

0.26

izontal

0.26

izable

0.25

Activations Density 0.009%

Orthodontics and orthopedics

No Comments

No Known Activations