INDEX

Explanations

not

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

onis

-0.31

èŀį

-0.27

ä¸įæŃ¢

-0.26

ä¸įå®Į

-0.26

OMET

-0.26

.chapter

-0.25

nicas

-0.24

.getStatus

-0.24

med

-0.24

 progressive

-0.24

POSITIVE LOGITS

 Associate

0.28

 compat

0.28

_associ

0.27

ISCO

0.27

 Phaser

0.26

 equivalent

0.25

ãģĭãģª

0.25

odal

0.24

*,

0.24

çĶ³è¯·

0.24

Activations Density 0.004%

not

No Comments

No Known Activations