INDEX

Explanations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bon

-0.27

!(

-0.25

 sÃ¸

-0.25

äºĨä¸Ģä»½

-0.24

cakes

-0.24

 senior

-0.24

éĥģ

-0.24

 Ð¿ÑĢÐ°Ð²Ð¸ÑĤÐµÐ»ÑĮ

-0.23

<%=

-0.23

Ð»ÐµÐ½

-0.23

POSITIVE LOGITS

ä»Ģä¹Īåľ°æĸ¹

0.25

çĶª

0.25

chn

0.24

ForResult

0.24

BeNull

0.23

weis

0.23

ä¿Ĥ

0.23

riage

0.23

TECT

0.23

aho

0.23

Activations Density 25.274%

related

No Comments

No Known Activations