INDEX

Explanations

Spreading information

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

å®Įæķ´æĢ§

-0.31

ä¸Ľ

-0.29

èĴ¸

-0.27

éĢģè´§

-0.27

nell

-0.27

 integrity

-0.26

iller

-0.25

 services

-0.25

 Laden

-0.25

ç²¾

-0.25

POSITIVE LOGITS

casting

0.29

 casting

0.28

.Parameters

0.27

ddl

0.25

.transition

0.25

 Cellular

0.25

 pois

0.24

 indoors

0.24

 Casting

0.24

iteration

0.24

Activations Density 0.020%

Spreading information

No Comments

No Known Activations