INDEX

Explanations

descriptions of experiments/processes

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

urus

-0.31

inion

-0.29

æľīæĿ¡ä»¶çļĦ

-0.28

æľīæĿ¡ä»¶

-0.26

 competitor

-0.26

éĤ£æ®µ

-0.25

-ed

-0.25

urb

-0.25

æĸ°åįİ

-0.24

otime

-0.24

POSITIVE LOGITS

Ent

0.34

Ent

0.29

iska

0.28

_CONV

0.26

èĽ¾

0.26

ÄŁ

0.26

).__

0.25

 cords

0.25

çĹħçĹĩ

0.24

 cabo

0.24

Activations Density 0.005%

descriptions of experiments/processes

No Comments

No Known Activations