INDEX

Explanations

spaghetti and twilight

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

manship

-0.26

desk

-0.26

èĶ¼

-0.25

mel

-0.24

æĥķ

-0.24

melon

-0.23

setAttribute

-0.23

AGIC

-0.23

yper

-0.22

 cultivated

-0.22

POSITIVE LOGITS

å¯ĵ

0.26

entes

0.26

è½½

0.25

 reinforcing

0.24

esi

0.24

rais

0.24

 Extr

0.24

çĦ¦çĤ¹

0.23

ieron

0.23

è¼ī

0.23

Activations Density 4.561%

spaghetti and twilight

No Comments

No Known Activations