INDEX

Explanations

body

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

_special

-0.25

EqualTo

-0.23

(instance

-0.23

éĩĮæĸ¯

-0.23

çī¹èī²

-0.23

icks

-0.23

è¾Ł

-0.23

 attrs

-0.22

ç¥¸

-0.22

ãģŁãĤĬ

-0.22

POSITIVE LOGITS

èº«

0.26

 Aviv

0.24

 race

0.24

 wouldn

0.23

OWL

0.23

 charge

0.22

å¤įåį°

0.22

vore

0.22

á»ĵng

0.22

åŀĴ

0.22

Activations Density 28.618%

body

No Comments

No Known Activations