INDEX

Explanations

fresh

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ë§ī

-0.27

 Screening

-0.26

Pic

-0.26

ä¼ļå½±åĵįåĪ°

-0.25

 verst

-0.25

 highest

-0.25

é¥¼

-0.24

 Galactic

-0.24

Pic

-0.24

 distribute

-0.24

POSITIVE LOGITS

éĥĬ

0.27

ÑħÐ¸

0.27

XCT

0.25

Arr

0.24

[arr

0.24

ancia

0.24

sig

0.24

oded

0.23

ermint

0.23

getContext

0.23

Activations Density 5.309%

fresh

No Comments

No Known Activations