INDEX

Explanations

photos

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 image

-0.40

 Image

-0.35

image

-0.34

åĽ¾åĥı

-0.32

-image

-0.32

 IMAGE

-0.32

pic

-0.31

 picture

-0.31

 Picture

-0.30

img

-0.30

POSITIVE LOGITS

syn

0.35

 synthesis

0.33

syn

0.29

Syn

0.29

Syn

0.29

ynthesis

0.29

åĲĪæĪĲ

0.28

ç¦»

0.27

iri

0.27

eos

0.26

Activations Density 0.005%

photos

No Comments

No Known Activations